1. A colorism-based computer-implemented advertising analysis system (100), comprising: a user interface (102) integrated into a user device (104) configured to allow a user to upload and select advertisements, choose the type of advertisement, view how skin tone and language are represented in the advertisement, understand the social meaning behind such representations; a communication network (106) configured to facilitate data exchange within the system (100); a processing unit (108) communicably connected to the user device (104) via the communication network (106) configured to execute programmed instructions for feature extraction, analytical evaluation, scoring, and classification of advertising content, wherein the processing unit (108) further comprises: a data input module (110) configured to receive data from the user device (104); a data processing module (112) configured to process, validate, format, and normalize received advertising content and user input data prior to analytical evaluation; a feature extraction module (114) configured to extract visual features including skin tone distribution, luminance values, contrast levels, facial prominence, and spatial positioning, and textual features including keywords, sentiment markers, and empowerment-related terminology; a representational analysis module (116) configured to analyze extracted visual features to determine complexion-based representational hierarchy and visual prominence patterns; a discursive analysis module (118), configured to analyze extracted textual and narrative features to identify implicit and explicit color-coded language and empowerment framing; a contextual analysis module (120), configured to map outputs of the representational and discursive analysis modules against socio-cultural parameters including caste, class, gender roles, and postcolonial identity indicators relevant to the Indian context; a weight assignment module (122) configured to assign predefined weights to visual, linguistic, and contextual indicators based on analytical significance; a scoring module (124) configured to compute a visual bias score based on weighted analytical outputs generated by the representational analysis module, the discursive analysis module, and the contextual analysis module; a classification module (126) configured to categorize the advertising content into predefined color-bias classes based on the computed visual bias score and evaluated socio-cultural parameters; a comparative analysis module (128) configured to compare classified advertising content across matrimonial, workplace, and motherhood advertisement categories to identify cross-domain bias patterns; and an output module (130), configured to generate a classification report comprising the visual bias score, the assigned color-bias category, and an explanatory summary derived from the analysis modules.

2. The system (100) as claimed in claim 1, wherein the system (100) further comprises a cloud data base (132) configured to store extracted features, computed scores, classification outcomes, and historical advertisement datasets for subsequent analytical comparison.

3. The system (100) as claimed in claim 1, wherein the data processing module (112) is configured to perform noise reduction, frame segmentation, metadata extraction, and format standardization of multimedia advertising inputs.

4. The system (100) as claimed in claim 1, wherein the feature extraction module (114) is further configured to compute luminance ratios, tonal variance indices, and contrast differentials across detected facial regions.

5. The system (100) as claimed in claim 1, wherein the discursive analysis module (118) is configured to perform dependency parsing and semantic relationship mapping to identify narrative framing patterns associated with complexion descriptors.

6. The system (100) as claimed in claim 1, wherein the representational analysis module (116) is configured to determine prominence ranking based on subject size, frame positioning, exposure duration, and foreground-background differentiation.

7. The system (100) as claimed in claim 1, wherein the weight assignment module (122) is configured to dynamically adjust assigned weights using rule-based calibration or trained model parameters derived from previously analysed advertising datasets.

8. The system (100) as claimed in claim 1, wherein the scoring module (124) performs a mathematical aggregation operation combining weighted outputs of the representational, discursive, and contextual analysis modules to compute the visual bias score.

9. The system (100) as claimed in claim 1, wherein the comparative analysis module (128) is configured to perform cross-category statistical comparison using clustering and pattern recognition techniques across advertisement domains.

10. A method (200) for colorism-Based Computer-Implemented Advertising Analysis relating to analysis of color-based bias in advertising content, the method (200) comprising; guiding and selecting advertisements, choose the type of advertisement, view how skin tone and language are represented in the advertisement, understand the social meaning behind such representations via a user interface (102) integrated into a user device (104); facilitating data exchange within the system (100) via a communication network (106); facilitating data exchange within the system (100) via a communication network (106); executing programmed instructions for representational analysis, discursive analysis, contextual evaluation, bias score computation, and classification of advertising content via a processing unit (108) comprising a representational analysis module (116), a discursive analysis module (118), a contextual analysis module (120), weight assignment module (122), a scoring module (124), and a classification module (126); processing, validating, and normalizing the received advertisement data; extracting visual features including skin tone distribution, luminance values, contrast levels, facial prominence, and spatial positioning and extracting textual features including keywords, sentiment markers, and narrative descriptors; analyzing the extracted visual features to determine complexion-based representational hierarchy and visual prominence patterns; analyzing the extracted textual and narrative features to identify implicit and explicit color-coded language and empowerment framing; mapping outputs of visual analysis and textual analysis against socio-cultural parameters including caste, class, gender roles, and postcolonial identity indicators; assigning predefined weights to visual indicators, linguistic indicators, and contextual indicators; computing a composite visual bias score through algorithmic aggregation of the weighted indicators using programmed scoring routines; classifying the advertisement data into predefined color-bias categories based on the computed visual bias score and evaluated socio-cultural parameters; and generating a classification report comprising the visual bias score, assigned color-bias category, and an explanatory analytical summary.

Description:FIELD OF DISCLOSURE
[0001] The present disclosure relates to the field of digital media analysis and socio-cultural computing, and more particularly to a colorism-based computer-implemented advertising analysis system for identifying, evaluating, and interpreting color-based bias and representational inequalities in advertising content.
BACKGROUND OF THE DISCLOSURE
[0002] Advertising media significantly influences social perception, identity formation, and standards of beauty across cultures. Despite increasing attention toward inclusivity, subtle and systemic forms of color-based bias continue to persist in visual and discursive representations. These biases often manifest through preferential portrayal, linguistic framing, and narrative positioning, yet remain difficult to detect through conventional analytical approaches.
[0003] The system provides a computer-implemented technique for examining color-based representation in advertising environments through structured evaluation of visual content and associated narrative elements within defined socio-cultural parameters. The system enables systematic identification, organization, and assessment of representation patterns across advertising materials using a technology-enabled framework. By moving beyond manual observation, the system supports data-driven interpretation of representational trends, intensity of bias, and contextual relevance within advertising content. The system further enables standardized, repeatable, and scalable evaluation of advertising materials across multiple formats and datasets. This reduces subjectivity in assessment, improves analytical consistency, and supports comparative analysis across campaigns, time periods, and demographic contexts, thereby facilitating structured monitoring and reporting of representation patterns.
[0004] The system advances the field by enabling interpretive analysis that aligns cultural context with representational outcomes, thereby supporting policy discourse, media accountability, and academic research. The present system facilitates broader societal examination of how advertising content reflects and reinforces social hierarchies, making it particularly relevant in jurisdictions where color-based representation intersects with historical, cultural, and socio-economic narratives.
[0005] Various existing techniques in advertising analysis primarily focus on consumer engagement metrics, sentiment evaluation, and brand perception studies. Such approaches emphasize market performance and audience response rather than representational equity or socio-cultural implications. As a result, these methods fail to identify subtle forms of visual hierarchy, linguistic framing, and contextual associations linked to complexion-based representation.
[0006] Certain research-oriented tools and content analysis systems attempt qualitative evaluation of representation within media; however, they rely heavily on manual interpretation and subjective judgment. These methods lack standardization, are difficult to scale across large datasets, and are prone to inconsistency across evaluators. The absence of structured analytical system limits their effectiveness in generating comparable or reproducible outcomes.
[0007] In many known arrangements, prior technological solutions addressing bias in media largely concentrate on general discrimination detection or sentiment classification without contextual grounding in socio-cultural realities. They do not sufficiently account for layered social indicators, cultural symbolism, and representational positioning specific to advertising environments. Consequently, such approaches produce fragmented insights, lack contextual depth, and fail to provide comprehensive analytical understanding of color-based bias in advertising content.
[0008] Thus, in light of the above-stated discussion, there exists a need for a colorism-based computer-implemented advertising analysis system for identifying and interpreting such representational patterns at scale.
SUMMARY OF THE DISCLOSURE
[0009] The following is a summary description of illustrative embodiments of the invention. It is provided as a preface to assist those skilled in the art to more rapidly assimilate the detailed design discussion which ensues and is not intended in any way to limit the scope of the claims which are appended hereto in order to particularly point out the invention.
[0010] According to illustrative embodiments, the present disclosure focuses on a colorism-based computer-implemented advertising analysis system which overcomes the above-mentioned disadvantages or provide the users with a useful or commercial choice.
[0011] An objective of the present disclosure is to enable automated assessment of advertising material to identify patterns associated with color-based representation in visual and textual contexts.
[0012] An objective of the present disclosure is to facilitate integrated evaluation of imagery, language, and contextual cues to generate a holistic understanding of representational trends.
[0013] An objective of the present disclosure is to provide a standardized mechanism for computing analytical indicators that reflect the intensity and nature of representational bias.
[0014] Another objective of the present disclosure is to enhance scalability of media analysis by enabling large-scale processing of advertising datasets from multiple platforms.
[0015] Another objective of the present is to facilitate evidence-based academic research, regulatory assessment, and ethical advertising practices through structured analytical outputs.
[0016] Another objective of the present disclosure is to support longitudinal evaluation of advertising content to identify shifts in representational patterns over time.
[0017] Another objective of the present disclosure is to enable contextual interpretation aligned with socio-cultural realities to ensure that analysis remains grounded in societal frameworks.
[0018] Another objective of the present disclosure is to provide actionable insights that can inform inclusive media design and responsible communication strategies.
[0019] Yet another objective of the present disclosure is to enable interoperable reporting formats that support integration with external evaluation systems and research platforms.
[0020] Yet another objective of the present disclosure is to bridge the gap between technological analysis and social interpretation by enabling systematic exploration of representational dynamics embedded in media environments.
[0021] In the light of the above, a colorism-based computer-implemented advertising analysis system is disclosed herein. The system comprises a user interface integrated into a user device configured to allow a user to upload and select advertisements, choose the type of advertisement, view how skin tone and language are represented in the advertisement, understand the social meaning behind such representations. The system also includes a communication network configured to facilitate data exchange within the system. The system also includes a processing unit communicably connected to the user device via the communication network configured to execute programmed instructions for feature extraction, analytical evaluation, scoring, and classification of advertising content, wherein the processing unit further comprises a data input module configured to receive data from the user device, a data preprocessing module configured to process, validate, format, and normalize received advertising content and user input data prior to analytical evaluation, a feature extraction module configured to extract visual features including skin tone distribution, luminance values, contrast levels, facial prominence, and spatial positioning, and textual features including keywords, sentiment markers, and empowerment-related terminology, a representational analysis module configured to analyze extracted visual features to determine complexion-based representational hierarchy and visual prominence patterns, a discursive analysis module, configured to analyze extracted textual and narrative features to identify implicit and explicit color-coded language and empowerment framing, a contextual analysis module, configured to map outputs of the representational and discursive analysis modules against socio-cultural parameters including caste, class, gender roles, and postcolonial identity indicators relevant to the Indian context, a weight assignment module configured to assign predefined weights to visual, linguistic, and contextual indicators based on analytical significance, a scoring module configured to compute a visual bias score based on weighted analytical outputs generated by the representational analysis module, the discursive analysis module, and the contextual analysis module, a classification module configured to categorize the advertising content into predefined color-bias classes based on the computed visual bias score and evaluated socio-cultural parameters, a comparative analysis module configured to compare classified advertising content across matrimonial, workplace, and motherhood advertisement categories to identify cross-domain bias patterns and an output module, configured to generate a classification report comprising the visual bias score, the assigned color-bias category, and an explanatory summary derived from the analysis modules.
[0022] In one embodiment, the system further comprises a cloud data base configured to store extracted features, computed scores, classification outcomes, and historical advertisement datasets for subsequent analytical comparison.
[0023] In one embodiment, the data processing module in the system is configured to perform noise reduction, frame segmentation, metadata extraction, and format standardization of multimedia advertising inputs.
[0024] In one embodiment, feature extraction module in the system is further configured to compute luminance ratios, tonal variance indices, and contrast differentials across detected facial regions.
[0025] In one embodiment, the representational analysis module in the system is configured to determine prominence ranking based on subject size, frame positioning, exposure duration, and foreground-background differentiation.
[0026] In one embodiment, the weight assignment module in the system is configured to dynamically adjust assigned weights using rule-based calibration or trained model parameters derived from previously analysed advertising datasets.
[0027] In one embodiment, the scoring module in the system performs a mathematical aggregation operation combining weighted outputs of the representational, discursive, and contextual analysis modules to compute the visual bias score.
[0028] In one embodiment, the comparative analysis module in the system is configured to perform cross-category statistical comparison using clustering and pattern recognition techniques across advertisement domains.
[0029] In light of the above, in one aspect of the present disclosure, a method for colorism-based computer-implemented advertising analysis is disclosed herein. The method comprises uploading and selecting advertisements, choose the type of advertisement, view how skin tone and language are represented in the advertisement, understand the social meaning behind such representations via a user interface integrated into a user device. The method includes facilitating data exchange within the system via a communication network. The method comprises executing programmed instructions for representational analysis, discursive analysis, contextual evaluation, bias score computation, and classification of advertising content via a processing unit comprising a representational analysis module, a discursive analysis module, a contextual analysis module, weight assignment module, a scoring module, and a classification module. The method includes processing, validating, and normalizing the received advertisement data. The method includes extracting visual features including skin tone distribution, luminance values, contrast levels, facial prominence, and spatial positioning and extracting textual features including keywords, sentiment markers, and narrative descriptors. The method comprises analyzing the extracted visual features to determine complexion-based representational hierarchy and visual prominence patterns. The method includes analyzing the extracted textual and narrative features to identify implicit and explicit color-coded language and empowerment framing. The method includes mapping outputs of visual analysis and textual analysis against socio-cultural parameters including caste, class, gender roles, and postcolonial identity indicators. The method comprises assigning predefined weights to visual indicators, linguistic indicators, and contextual indicators. The method includes computing a composite visual bias score through algorithmic aggregation of the weighted indicators using programmed scoring routines. The method comprises classifying the advertisement data into predefined color-bias categories based on the computed visual bias score and evaluated socio-cultural parameters. The method includes generating a classification report comprising the visual bias score, assigned color-bias category, and an explanatory analytical summary.
[0030] These and other advantages will be apparent from the present application of the embodiments described herein.
[0031] The preceding is a simplified summary to provide an understanding of some embodiments of the present invention. This summary is neither an extensive nor exhaustive overview of the present invention and its various embodiments. The summary presents selected concepts of the embodiments of the present invention in a simplified form as an introduction to the more detailed description presented below. As will be appreciated, other embodiments of the present invention are possible utilizing, alone or in combination, one or more of the features set forth above or described in detail below.
[0032] These elements, together with the other aspects of the present disclosure and various features are pointed out with particularity in the claims annexed hereto and form a part of the present disclosure. For a better understanding of the present disclosure, its operating advantages, and the specified object attained by its uses, reference should be made to the accompanying drawings and descriptive matter in which there are illustrated exemplary embodiments of the present disclosure.
BRIEF DESCRIPTION OF THE DRAWINGS
[0033] To describe the technical solutions in the embodiments of the present disclosure or in the prior art more clearly, the following briefly describes the accompanying drawings required for describing the embodiments or the prior art. Apparently, the accompanying drawings in the following description merely show some embodiments of the present disclosure, and a person of ordinary skill in the art can derive other implementations from these accompanying drawings without creative efforts. All of the embodiments or the implementations shall fall within the protection scope of the present disclosure.
[0034] The advantages and features of the present disclosure will become better understood with reference to the following detailed description taken in conjunction with the accompanying drawing, wherein like reference numerals indicate corresponding elements:
[0035] FIG. 1 illustrates a block diagram of a colorism-based computer-implemented advertising analysis system, in accordance with an exemplary embodiment of the present disclosure;
[0036] FIG. 2 illustrates a flowchart of a method for colorism-based computer-implemented advertising analysis, in accordance with an exemplary embodiment of the present disclosure;
[0037] Like reference, numerals refer to like parts throughout the description of several views of the drawing.
[0038] The drawings are intended to provide illustrative embodiments of the present disclosure to facilitate understanding of the system and its operational workflow. The drawings are not intended to limit the scope of the present disclosure and are not necessarily drawn to scale.
DETAILED DESCRIPTION OF THE DISCLOSURE
[0039] The following is a detailed description of embodiments of the disclosure depicted in the accompanying drawings. The embodiments are in such detail as to communicate the disclosure. However, the amount of detail offered is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the present disclosure.
[0040] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. It may be apparent to one skilled in the art that embodiments of the present disclosure may be practiced without some of these specific details.
[0041] Various terms as used herein are shown below. To the extent a term is used, it should be given the broadest definition persons in the pertinent art have given that term as reflected in printed publications and issued patents at the time of filing.
[0042] The terms “a” and “an” herein do not denote a limitation of quantity, but rather denote the presence of at least one of the referenced items.
[0043] The terms “having”, “comprising”, “including”, and variations thereof signify the presence of a component.
[0044] Referring now to FIG. 1 and FIG. 2 to describe various exemplary embodiments of the present disclosure. FIG. 1 illustrates a block diagram of a colorism-based computer-implemented advertising analysis system, in accordance with an exemplary embodiment of the present disclosure.
[0045] The system 100 may include a user interface 102 integrated into a user device 104, a communication network 106, and a processing unit 108. The processing unit 108 may further include a data input module 110, a data processing module 112, a feature extraction module 114, a representational analysis module 116, a discursive analysis module 118, a contextual analysis module 120, a weight assignment module 122, a scoring module 124, a classification module 126, a comparative analysis module 128, and an output module 130.
[0046] The user interface 102 may be configured to enable a user to upload advertising content, select advertisement categories, provide contextual information, and review analytical results. The interface may support interaction through graphical controls and structured prompts to facilitate ease of use.
[0047] The user device 104 provides the operational platform through which the system is accessed. It supports submission of advertising material and display of outputs generated by the system.
[0048] The communication network 106 may be configured to connect the user device 104 and the processing unit 108 for transmission of advertising content, user inputs, and analytical outputs. The communication network 106 comprises an encrypted data transmission protocol configured to ensure secure transfer of advertising inputs and analytical outputs between system components.
[0049] The processing unit 108 performs the core technical operations of the invention and acts as the central computational environment in which all analytical functions are executed. It coordinates reception of data, execution of programmed instructions, and generation of outputs. The processing unit 108 integrates multiple functional modules to process data, including a data input module 110, a data preprocessing module 112, a feature extraction module 114, a representational analysis module 116, a discursive analysis module 118, a contextual analysis module 120, a weight assignment module 122, a scoring module 124, a classification module 126, a comparative analysis module 128 and an output module 130.
[0050] The data input module 110 may be configured to receive advertising content and user inputs from the user device 104. The data input module 110 may handle different media formats including images, videos, audio content, and textual data.
[0051] The data processing module 112 may be configured to process, validate, format, and normalize the received advertising content prior to analytical evaluation. This module may ensure consistency in data representation for subsequent analysis.
[0052] In one embodiment of the present invention, the data processing module 112 is configured to perform noise reduction, frame segmentation, metadata extraction, and format standardization of multimedia advertising inputs.
[0053] The feature extraction module 114 identifies and isolates meaningful attributes from advertising material and converts them into structured analytical data. It examines visual content to identify tonal distribution, brightness variation, facial prominence, spatial placement, and other visible characteristics that influence perception. In textual and narrative content, it identifies keywords, tone of expression, contextual phrases, and narrative emphasis. The feature extraction module 114 transforms these elements into quantifiable representations that can be further evaluated by subsequent analytical stages. It operates through pattern identification and structured parsing to ensure that relevant information is captured without distortion. By converting complex multimedia material into organized analytical inputs, the feature extraction module 114 establishes the foundation for reliable evaluation. Its functioning ensures that visual and textual indicators are consistently identified across different advertisements and prepared for deeper interpretive analysis.
[0054] In one embodiment of the present invention, the feature extraction module 114 is further configured to compute luminance ratios, tonal variance indices, and contrast differentials across detected facial regions.
[0055] The representational analysis module 116 evaluates extracted visual features to determine how individuals are portrayed in relation to complexion and prominence within advertising imagery. It examines patterns of placement, visibility, and emphasis to understand whether visual hierarchies are present. The representational analysis module 116 interprets tonal variation and visual focus to identify patterns that may suggest preference, marginalization, or symbolic positioning. It studies compositional balance and visual framing to assess whether portrayals reinforce or challenge established representational norms. The representational analysis module 116 processes these visual indicators systematically to produce analytical outcomes reflecting the nature of representation within the advertisement. By focusing on visual portrayal rather than isolated imagery, the module enables deeper interpretation of representational dynamics. Its functioning contributes to identifying structured patterns that may otherwise remain unnoticed in conventional viewing.
[0056] In one embodiment of the present invention, the representational analysis module 116 is configured to determine prominence ranking based on subject size, frame positioning, exposure duration, and foreground-background differentiation.
[0057] The discursive analysis module 118 evaluates linguistic and narrative elements present in advertising content. It examines descriptive expressions, taglines, verbal cues, and narrative structures to understand how language contributes to perception and meaning. The discursive analysis module 118 identifies explicit and implicit references that may shape attitudes toward complexion, identity, and desirability. It interprets tone, emphasis, and framing within textual content to determine whether narratives reinforce stereotypes, aspirations, or cultural associations. The discursive analysis module 118 further examines the interaction between language and imagery to understand how both collectively influence representation. By translating narrative cues into analytical indicators, the discursive analysis module 118 supports structured interpretation of messaging within advertising. Its role ensures that the system 100 does not rely solely on visual data but also incorporates language-driven perception in the overall evaluation process.
[0058] In one embodiment of the present invention, the discursive analysis module 118 is configured to perform dependency parsing and semantic relationship mapping to identify narrative framing patterns associated with complexion descriptors.
[0059] The contextual analysis module 120 interprets analytical findings within broader socio-cultural environments. It correlates visual and linguistic indicators with cultural narratives, social positioning, and identity markers relevant to the environment in which the advertisement exists. The contextual analysis module 120 evaluates how representation aligns with social hierarchies, historical influences, and symbolic associations that shape public perception. It considers how portrayals may reflect gender expectations, social mobility narratives, and aspirational constructs embedded in media. Through this interpretive process, the module situates analytical outcomes within a meaningful social framework rather than treating them as isolated observations. It supports deeper understanding of representation by linking analytical indicators to contextual meaning. This ensures that outputs generated by the system reflect not only technical evaluation but also socially grounded interpretation of advertising content.
[0060] The weight assignment module 122 assigns relative importance to analytical indicators derived from visual, linguistic, and contextual evaluations. It establishes a structured framework through which different analytical outcomes are balanced to avoid disproportionate influence from any single indicator. The weight assignment module 122 evaluates relevance, intensity, and consistency of indicators and applies corresponding weight values. These weight values enable systematic integration of diverse analytical findings into a unified evaluative structure. By regulating the influence of multiple parameters, the weight assignment module 122 ensures fairness and analytical stability in subsequent computations. It also supports adaptability by allowing recalibration of weight values when analytical priorities or evaluation contexts change. The structured weighting mechanism enhances reliability and ensures that final outcomes reflect a balanced interpretation of all analytical inputs.
[0061] In one embodiment of the present invention, the weight assignment module 122 is configured to dynamically adjust assigned weights using rule-based calibration or trained model parameters derived from previously analysed advertising datasets.
[0062] The scoring module 124 converts weighted analytical indicators into measurable values that represent the degree and nature of representational bias within advertising content. It aggregates outputs from prior analytical stages and processes them through computational evaluation methods to produce a unified score. The scoring module 124 ensures consistency in scoring across different advertisements by applying standardized evaluation logic. It generates results that are interpretable and comparable, enabling assessment of relative bias intensity. The scoring process also supports reproducibility, allowing similar inputs to produce consistent outcomes. By transforming qualitative indicators into quantitative values, the scoring module bridges interpretive analysis and measurable assessment. This enables the system to provide objective and structured outputs suitable for research, policy evaluation, and media analysis.
[0063] In one embodiment of the present invention, the scoring module 124 performs a mathematical aggregation operation combining weighted outputs of the representational, discursive, and contextual analysis modules to compute the visual bias score.
[0064] The classification module 126 interprets computed scores and analytical indicators to categorize advertising content into predefined representational classes. It evaluates relationships among visual portrayal, linguistic framing, and contextual interpretation to determine the most appropriate category. The classification module 126 applies structured decision logic to ensure consistency in classification outcomes. It enables grouping of advertisements based on shared patterns of representation and bias characteristics. The classification process supports comparative analysis by creating standardized categories that can be examined across datasets. It also enhances interpretability by translating complex analytical findings into understandable classifications. Through its functioning, the classification module 126 allows users to identify patterns, trends, and recurring representational structures within advertising environments.
[0065] The comparative analysis module 128 enables cross-domain evaluation of classified advertising content to identify broader trends and recurring patterns. It examines differences and similarities among advertisements belonging to various thematic or social categories. The comparative analysis module 128 analyzes how representational practices vary across contexts and how bias indicators shift across domains. It supports longitudinal comparison by enabling evaluation of advertisements across different time periods or campaigns. Through structured comparison, the module helps reveal systemic patterns that may not be visible within isolated analysis. It also supports academic and regulatory assessment by enabling evidence-based examination of representational practices. The comparative analysis module 128 enhances the overall analytical capacity of the system by extending evaluation beyond individual advertisements toward pattern recognition and trend identification.
[0066] In one embodiment of the present invention, the comparative analysis module 128 is configured to perform cross-category statistical comparison using clustering and pattern recognition techniques across advertisement domains.
[0067] The output module 130 generates a structured classification report that communicates analytical findings in an understandable format. It integrates measurable scores, categorical classification, and interpretive summaries into a unified report. The output module 130 ensures clarity and accessibility of results so that users from non-technical backgrounds can interpret outcomes without difficulty. It supports visualization and structured presentation of findings to improve comprehension. The generated output enables researchers, policymakers, and media professionals to understand representational patterns and draw informed conclusions. The output module 130 also supports documentation and storage of analytical results for future reference, comparison, and reporting. By transforming complex analytical processes into readable outcomes, the output module 130 completes the functional cycle of the invention.
[0068] In one embodiment of the present invention, the system 100 further comprises a cloud data base 132 configured to store extracted features, computed scores, classification outcomes, and historical advertisement datasets for subsequent analytical comparison.
[0069] FIG. 2 illustrates a flowchart of a method for colorism-based computer-implemented advertising analysis in accordance with an exemplary embodiment of the present disclosure;
[0070] The method 200 may include, at step 202, uploading and selecting advertisements, choose the type of advertisement, view how skin tone and language are represented in the advertisement, understand the social meaning behind such representations via a user interface 102 integrated into a user device 104, at step 204, facilitating data exchange within the system 100 via a communication network 106, at step 206, processing, validating, and normalizing the received advertisement data, at step 208, executing programmed instructions for representational analysis, discursive analysis, contextual evaluation, bias score computation, and classification of advertising content via a processing unit (108) comprising a representational analysis module (116), a discursive analysis module (118), a contextual analysis module (120), weight assignment module (122), a scoring module (124), and a classification module (126), at step 210, extracting visual features including skin tone distribution, luminance values, contrast levels, facial prominence, and spatial positioning, at step 212, extracting textual features including keywords, sentiment markers, and narrative descriptors, at step 214, analyzing the extracted visual features to determine complexion-based representational hierarchy and visual prominence patterns, at step 216, analyzing the extracted textual and narrative features to identify implicit and explicit color-coded language and empowerment framing, at step 218, mapping outputs of visual analysis and textual analysis against socio-cultural parameters including caste, class, gender roles, and postcolonial identity indicators, at step 220, assigning predefined weights to visual indicators, linguistic indicators, and contextual indicators, at step 222, computing a composite visual bias score through algorithmic aggregation of the weighted indicators using programmed scoring routines, at step 224, classifying the advertisement data into predefined color-bias categories based on the computed visual bias score and evaluated socio-cultural parameters and at step 226, generating a classification report comprising the visual bias score, assigned color-bias category, and an explanatory analytical summary.
[0071] In the best mode of operation, the system 100 is configured such that a user accesses advertisement content through a user interface 102 integrated into a user device 104, wherein the user selects and uploads advertisement data including image, video, audio-visual, or textual material along with optional contextual parameters. The uploaded data is transmitted via the communication network 106 to the processing unit 108, which performs validation, normalization, and preprocessing to convert the advertisement into structured machine-readable form. The processing unit 108 executes programmed instructions through a representational analysis module 116 to extract visual attributes including skin tone distribution, luminance gradients, facial prominence, spatial positioning, and contrast levels, while a discursive analysis module 118 extracts textual features such as keywords, sentiment markers, narrative framing, and implicit color-coded language. A contextual analysis module 120 maps the extracted outputs against predefined socio-cultural parameters including caste, class, gender roles, and postcolonial identity indicators. A weight assignment module 122 assigns calibrated weights to visual, linguistic, and contextual indicators, after which a scoring module 124 computes a composite visual bias score through algorithmic aggregation routines. A classification module 126 categorizes the advertisement into predefined color-bias categories based on computed thresholds. A comparative analysis module 128 configured to compare computed bias scores and extracted attributes with reference datasets, historical advertisement records, or predefined benchmarks to determine relative deviation, trend indicators, and contextual bias positioning and the system 100 generates a structured classification report comprising the visual bias score, assigned category, and an explanatory analytical summary, which is transmitted back to the user interface 102 for display.
[0072] The present disclosure enables standardized and repeatable evaluation of advertising content by combining structured analysis with contextual interpretation. This approach reduces reliance on subjective human judgment and enhances consistency in analytical outcomes.
[0073] The system 100 provides a structured and technology-driven framework for objective evaluation of advertisement content by transforming subjective socio-representational assessment into a quantifiable analytical process. By automating extraction, normalization, and multi-parameter evaluation of visual and textual elements, the system 100 improves consistency, accuracy, and reproducibility in bias detection. The algorithmic computation of composite scores reduces human interpretational variability and enables standardized classification across diverse media formats, languages, and cultural contexts. The architecture supports scalable processing of large advertisement datasets with improved computational efficiency and reduced manual intervention. Further, the generation of transparent analytical reports enhances traceability and auditability, allowing stakeholders to understand the basis of classification outcomes. Overall, the system 100 enhances technical reliability, minimizes ambiguity in representational evaluation, and provides a measurable decision-support mechanism for ethical and inclusive advertising assessment.
[0074] While the invention has been described in connection with what is presently considered to be the most practical and various embodiments, it will be understood that the invention is not to be limited to the disclosed embodiments, but on the contrary, is intended to cover various modifications and equivalent arrangements included within the scope of the appended claims.
[0075] A person of ordinary skill in the art may be aware that, in combination with the examples described in the embodiments disclosed in this specification, units and algorithm steps may be implemented by electronic hardware, computer software, or a combination thereof.
[0076] The foregoing descriptions of specific embodiments of the present disclosure have been presented for purposes of illustration and description. They are not intended to be exhaustive or to limit the present disclosure to the precise forms disclosed, and many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described to best explain the principles of the present disclosure and its practical application, and to thereby enable others skilled in the art to best utilize the present disclosure and various embodiments with various modifications as are suited to the particular use contemplated. It is understood that various omissions and substitutions of equivalents are contemplated as circumstances may suggest or render expedient, but such omissions and substitutions are intended to cover the application or implementation without departing from the scope of the present disclosure.
[0077] Disjunctive language such as the phrase “at least one of X, Y, Z,” unless specifically stated otherwise, is otherwise understood with the context as used in general to present that an item, term, etc., may be either X, Y, or Z, or any combination thereof (e.g., X, Y, and/or Z). Thus, such disjunctive language is not generally intended to, and should not, imply that certain embodiments require at least one of X, at least one of Y, or at least one of Z to each be present.
[0078] In a case that no conflict occurs, the embodiments in the present disclosure and the features in the embodiments may be mutually combined. The foregoing descriptions are merely specific implementations of the present disclosure, but are not intended to limit the protection scope of the present disclosure. Any variation or replacement readily figured out by a person skilled in the art within the technical scope disclosed in the present disclosure shall fall within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.
, Claims:I/We Claim:
1. A colorism-based computer-implemented advertising analysis system (100), comprising:
a user interface (102) integrated into a user device (104) configured to allow a user to upload and select advertisements, choose the type of advertisement, view how skin tone and language are represented in the advertisement, understand the social meaning behind such representations;
a communication network (106) configured to facilitate data exchange within the system (100);
a processing unit (108) communicably connected to the user device (104) via the communication network (106) configured to execute programmed instructions for feature extraction, analytical evaluation, scoring, and classification of advertising content, wherein the processing unit (108) further comprises:
a data input module (110) configured to receive data from the user device (104);
a data processing module (112) configured to process, validate, format, and normalize received advertising content and user input data prior to analytical evaluation;
a feature extraction module (114) configured to extract visual features including skin tone distribution, luminance values, contrast levels, facial prominence, and spatial positioning, and textual features including keywords, sentiment markers, and empowerment-related terminology;
a representational analysis module (116) configured to analyze extracted visual features to determine complexion-based representational hierarchy and visual prominence patterns;
a discursive analysis module (118), configured to analyze extracted textual and narrative features to identify implicit and explicit color-coded language and empowerment framing;
a contextual analysis module (120), configured to map outputs of the representational and discursive analysis modules against socio-cultural parameters including caste, class, gender roles, and postcolonial identity indicators relevant to the Indian context;
a weight assignment module (122) configured to assign predefined weights to visual, linguistic, and contextual indicators based on analytical significance;
a scoring module (124) configured to compute a visual bias score based on weighted analytical outputs generated by the representational analysis module, the discursive analysis module, and the contextual analysis module;
a classification module (126) configured to categorize the advertising content into predefined color-bias classes based on the computed visual bias score and evaluated socio-cultural parameters;
a comparative analysis module (128) configured to compare classified advertising content across matrimonial, workplace, and motherhood advertisement categories to identify cross-domain bias patterns; and
an output module (130), configured to generate a classification report comprising the visual bias score, the assigned color-bias category, and an explanatory summary derived from the analysis modules.
2. The system (100) as claimed in claim 1, wherein the system (100) further comprises a cloud data base (132) configured to store extracted features, computed scores, classification outcomes, and historical advertisement datasets for subsequent analytical comparison.
3. The system (100) as claimed in claim 1, wherein the data processing module (112) is configured to perform noise reduction, frame segmentation, metadata extraction, and format standardization of multimedia advertising inputs.
4. The system (100) as claimed in claim 1, wherein the feature extraction module (114) is further configured to compute luminance ratios, tonal variance indices, and contrast differentials across detected facial regions.
5. The system (100) as claimed in claim 1, wherein the discursive analysis module (118) is configured to perform dependency parsing and semantic relationship mapping to identify narrative framing patterns associated with complexion descriptors.
6. The system (100) as claimed in claim 1, wherein the representational analysis module (116) is configured to determine prominence ranking based on subject size, frame positioning, exposure duration, and foreground-background differentiation.
7. The system (100) as claimed in claim 1, wherein the weight assignment module (122) is configured to dynamically adjust assigned weights using rule-based calibration or trained model parameters derived from previously analysed advertising datasets.
8. The system (100) as claimed in claim 1, wherein the scoring module (124) performs a mathematical aggregation operation combining weighted outputs of the representational, discursive, and contextual analysis modules to compute the visual bias score.
9. The system (100) as claimed in claim 1, wherein the comparative analysis module (128) is configured to perform cross-category statistical comparison using clustering and pattern recognition techniques across advertisement domains.
10. A method (200) for colorism-Based Computer-Implemented Advertising Analysis relating to analysis of color-based bias in advertising content, the method (200) comprising;
guiding and selecting advertisements, choose the type of advertisement, view how skin tone and language are represented in the advertisement, understand the social meaning behind such representations via a user interface (102) integrated into a user device (104);
facilitating data exchange within the system (100) via a communication network (106);
facilitating data exchange within the system (100) via a communication network (106);
executing programmed instructions for representational analysis, discursive analysis, contextual evaluation, bias score computation, and classification of advertising content via a processing unit (108) comprising a representational analysis module (116), a discursive analysis module (118), a contextual analysis module (120), weight assignment module (122), a scoring module (124), and a classification module (126);
processing, validating, and normalizing the received advertisement data;
extracting visual features including skin tone distribution, luminance values, contrast levels, facial prominence, and spatial positioning and extracting textual features including keywords, sentiment markers, and narrative descriptors;
analyzing the extracted visual features to determine complexion-based representational hierarchy and visual prominence patterns;
analyzing the extracted textual and narrative features to identify implicit and explicit color-coded language and empowerment framing;
mapping outputs of visual analysis and textual analysis against socio-cultural parameters including caste, class, gender roles, and postcolonial identity indicators;
assigning predefined weights to visual indicators, linguistic indicators, and contextual indicators;
computing a composite visual bias score through algorithmic aggregation of the weighted indicators using programmed scoring routines;
classifying the advertisement data into predefined color-bias categories based on the computed visual bias score and evaluated socio-cultural parameters; and
generating a classification report comprising the visual bias score, assigned color-bias category, and an explanatory analytical summary.