The present invention generally relates to a system and method to analyze data from the internet for a particular brand and particularly to a system and method for detecting sentiment about any brand related to tourism industry.
BACKGROUND
Most of the people use social media to read and review about brands. People follow social media influencer who promotes brand. The tourism industry has great potential to generate huge revenue. However, the tourism industries need to promote tourism. The tourism industry needs to develop their brand in order to promote tourism. The tourism industry can use digital platforms to develop the brand and to analyze the sentiment of the brand. The digital media may include, such as web chats, email messages, text messages, images, video files or audio files, information related to events, activities, and so on. The sharing of digital media can be carried out on a communication network such as a computer network. Nowadays, digital media platforms have encouraged new ways to communicate and share information/opinion between users. These networking platforms provide a platform for the number of users for sharing digital media. Most of the brands these days use these digital platforms to carry out branding about their brand and use various methods to increase the reputation and value of the brand in the eyes of their customers. An example of the use of this method can be seen in a software made for a tourism brand where the software for Tourism brand will search and analyze the posts, discussions, messages, tweets, etc where the users discuss the brand, the software analyses whether the voice/opinion of the users is positive, negative or neutral.
US8909771 discloses a method, apparatus, non-transitory computer readable storage medium, computer system, network, or system, is provided for using location information, 2D and 3D mapping, social media, and user behavior and information to provide alternative a consumer feedback social media analytics platforms for providing analytic measurements data of online

consumer feedback for global brand products or services of past, present or future customers, users, and/or target markets, for companies, organizations, government agencies, and the like, by electronically collecting and analyzing, on a networked computer system using a processor, qualitative or quantitative online social media online communications, activity, and online communications and activity relevant to consumer products or services, or promotions thereof, of interest, in order to provide targeted, location-based, 2D or 3D mapped, or impressions to generate online location information data or promotions to provide improved or desired customer perception or sentiment regarding a company's products, services or promotions thereof.
The existing invention does not provide accurate sentiment about the brand. Therefore, there is a need for an improved system to detect sentiment related to a particular tourism brand.
OBJECTIVE OF THE INVENTION
The main objective of the present invention is to construct a logical and contextual-based system to analyze sentiments related to a tourism brand.
Another objective of the present invention is to monitor sentiment related brand through computational analytics, more specifically for tourism brand.
Yet another objective of the present invention is to use artificial intelligence-based to analyze the sentiment related specifically to a tourism brand.
Yet another objective of the present invention is to collects visual as well as other types of data associated with the brand and analyze the sentiment related specifically to a tourism brand.
Yet another objective of the present invention is to help the user, effectively.
Further objectives, advantages, and features of the present invention will become apparent from the detailed description provided herein below, in which various embodiments of the disclosed invention is illustrated by way of example.
SUMMARY OF THE INVENTION

The present invention relates to a system and method for brand analytics. The system of the present includes an analytic server and a client computer. Herein each of the analytic servers includes an analytic server database, and a processor. The analytic server database stores non-transitory computer-readable instructions and a machine learning model operable stored in the analytic server database. The non-transitory computer-readable instructions containing a set of instructions configured to instruct the processor to perform sentiment analysis related to a particular brand by using the machine learning model and set of human-crafted rules, and generate a result by categorizing the sentiment related to a particular brand. The client computer is connected to the analytic server, wherein the set of instructions further transmit the generated sentiment to the client computer. Herein the context is identified out of the retrieved data based on contextual analysis, thus sentiment is determined from the context and further sentiment is categorization as negative, positive, and neutral. Herein the non-transitory computer-readable instructions further transmit the generated sentiment result to the client device.
The main advantage of the present invention is that the present invention helps to construct an artificial intelligence-based method to analyze sentiments related to a brand
Another advantage of the present invention is that the present invention helps to monitor brand sentiment accurately.
Yet another advantage of the present invention is that the present invention is easy and cost-effective.
Yet another advantage of the present invention is that the present invention is able to perform context-based analysis to identify sentiment related to the brand in the market.
Further objectives, advantages, and features of the present invention will become apparent from the detailed description provided herein below, in which various embodiments of the disclosed invention is illustrated by way of example.

BRIEF DESCRIPTION OF THE DRAWINGS
The accompanying drawings are incorporated in and constitute a part of this specification to provide a further understanding of the invention. The drawings illustrate one embodiment of the invention and together with the description, serve to explain the principles of the invention.
Fig.l. illustrates the block diagram of the present.
Fig.2. illustrates a rule-based method for brand analytics.
Fig. 3 illustrates an automatic method for brand analytics
DETAILED DESCRIPTION OF THE INVENTION
Definition
The terms "a" or "an", as used herein, are defined as one or as more than one. The term "plurality", as used herein, is defined as two as or more than two. The term "another", as used herein, is defined as at least a second or more. The terms "including" and/or "having", as used herein, are defined as comprising (i.e., open language). The term "coupled", as used herein, is defined as connected, although not necessarily directly, and not necessarily mechanically.
The term "comprising" is not intended to limit inventions to only claiming the present invention with such comprising language. Any invention using the term comprising could be separated into one or more claims using "consisting" or "consisting of claim language and is so intended. The term "comprising" is used interchangeably used by the terms "having" or "containing".
Reference throughout this document to "one embodiment", "certain embodiments", "an embodiment", "another embodiment", and "yet another embodiment" or similar terms means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, the appearances of such phrases or in various places throughout this specification are not necessarily all referring

to the same embodiment. Furthermore, the particular features, structures, or characteristics are combined in any suitable manner in one or more embodiments without limitation.
The term "or" as used herein is to be interpreted as an inclusive or meaning any one or any combination. Therefore, "A, B or C" means any of the following: "A; B; C; A and B; A and C; B and C; A, B and C". An exception to this definition will occur only when a combination of elements, functions, steps, or acts are in some way inherently mutually exclusive.
As used herein, the term "one or more" generally refers to, but not limited to, singular as well as the plural form of the term.
The drawings featured in the figures are to illustrate certain convenient embodiments of the present invention and are not to be considered as a limitation to that. Term "means" preceding a present participle of operation indicates the desired function for which there is one or more embodiments, i.e., one or more methods, devices, or apparatuses for achieving the desired function and that one skilled in the art could select from these or their equivalent in view of the disclosure herein and use of the term "means" is not intended to be limiting.
Fig.l. illustrates the block diagram of the system(lOO). The system(lOO) of the present includes an analytic server(102), and a client computer(108). Herein each of the analytic servers (102) includes an analytic server database(104), a processor(106). The analytic server(102) is connected to an external internet server(HO).
Fig.2. illustrates a rule-based method for brand analytics. In step(112), a set of human-crafted rules is created. In step(114), the set of human-crafted rules identify subjectivity, polarity, context, and the subject of an opinion about a brand, from the retrieved data. In step(116), the non-transitory computer-readable instructions are developed base on the set of human-crafted rules. In step(l 18), the non-transitory computer-readable instructions are feed into the analytic server database(104) of the analytic server(102). In step(120), further, the processor(106)

executes the non-transitory computer-readable instructions to identify subjectivity, polarity, context, and the subject of an opinion about a brand, from the retrieved data. Thus, sentiment related to the brand is determined based on subjectivity, polarity, context, and the subject of an opinion about the brand.
Fig.3 illustrates an automatic method for brand analytics. In step(122), the processing unit(106) executes computer-readable instructions to extract data related to a brand. In step(124), data are refined and labeled, thus creating a data set of specific words and context of the specific word. In step(126), the refined data set is fed into a classifier model to train the classifier model to identify the context of the specific word. In step(128), the classifier model is further tested and optimized. In step(130), the trained classifier model is further stored in the analytic server database(104) of the analytic server(102). In step(132), further, the processor(106) feed data into the trained classifier model to identify the context of the specific word. In step(134), thus, sentiment related to the brand is determined based on identifying the context of the specific word.
The present invention relates to a system and method for brand analytics. The system of the present includes an analytic server and a client computer. As used herein, the "server" refers to a piece of computer hardware that provides functionality for other programs or devices, called "clients" Herein each of the analytic servers includes an analytic server database, a processor. As used herein, the term "database" refers to a collection of information that is organized so that information can be easily accessed, managed, and updated, and "database" typically contains aggregations of data records or files. The analytic server database stores non-transitory computer-readable instructions and a machine learning model. The non-transitory computer-readable instructions containing a set of instructions configured to instruct the processor to perform sentiment analysis related to a particular brand by using the machine learning model and set of human-crafted rules, and generate a result by categorizing the sentiment related to a particular brand. The client computer is connected to the analytic server, wherein the set of instructions further transmit the generated sentiment to the

client computer. Herein the context is identified out of the retrieved data based on contextual analysis, thus sentiment is determined from the context and further sentiment is categorization as negative, positive, and neutral. Herein the non-transitory computer-readable instructions further transmit the generated sentiment result to the client device. In an embodiment, the analytic server is selected from a desktop computer, laptop, tab, and smartphone, cluster computers. In an embodiment, the computing server is connected to an external internet server to retrieve data for brand analysis.
In an embodiment, the present invention relates to a system and method for brand analytics. The system of the present includes one or more analytic servers and one or more client computers. Herein each of the one or more analytic servers includes an analytic server database, a processor. The analytic server database stores non-transitory computer-readable instructions and a machine learning model. The non-transitory computer-readable instructions containing a set of instructions configured to instruct the processor to perform sentiment analysis related to a particular brand by using the machine learning model and set of human-crafted rules, and generate a result by categorizing the sentiment related to a particular brand. The one or more client computers are connected to the one or more analytic servers, wherein the set of instructions further transmit the generated sentiment to the one or more client computers. Herein the context is identified out of the retrieved data based on contextual analysis, thus sentiment is determined from the context and further sentiment is categorization as negative, positive, and neutral. Herein the non-transitory computer-readable instructions further transmit the generated sentiment result to the one or more client devices. In an embodiment, the one or more analytic servers are selected from a desktop computer, laptop, tab and smartphone, cluster computers. In an embodiment, the one or more computing servers are connected to an external internet server to retrieve data for brand analysis.

In an embodiment, the present invention relates a method to determine sentiment related to a particular brand. A processor of an analytic server executes a set of methods. The method includes
A rule-based method, the method having
a set of human-crafted rules is created;
the set of human-crafted rules identify subjectivity, polarity, context, and the subject of an opinion about a brand, from the retrieved data;
the non-transitory computer-readable instructions are developed base on the set of human-crafted rules;
the non-transitory computer-readable instructions are feed into the analytic server database of the analytic server;
further, the processor executes the non-transitory computer-readable instructions to identify subjectivity, polarity, context, and the subject of an opinion about a brand, from the retrieved data;
thus, sentiment related to the brand is determined based on subjectivity, polarity, context, and the subject of an opinion about the brand.
In an embodiment, the non-transitory computer-readable instructions develop based on a set of human-crafted rules perform the sentiment analysis using different computational techniques selected from stemming, tokenization, part-of-speech tagging and parsing, lexicons.
In an embodiment, the non-transitory computer-readable instructions further perform at least one of a live search and trend-based search based on the one or more queries.
An automatic method, the methods having
the processing unit executes computer-readable instructions to extract data related to a brand;

data are refined and labeled, thus creating a data set of specific word and context of the specific word;
the refined data set is fed into a classifier model to train the classifier model to identify the context of the specific word;
the classifier model is further tested and optimized;
the trained classifier model is further stored in into the analytic server database of the analytic server;
further, the processor feed data into the trained classifier model to identify the context of the specific word;
thus, sentiment related to the brand is determined based on the identified context of the specific word;
wherein, the processor uses the results of both the rules-based method and automatic method to accurately determine the sentiment related to the brand and the further sentiment is categorization as negative, positive, and neutral.
wherein, the computing server is connected to an external internet server to retrieve data for brand analysis.
In an embodiment, the set of instructions further transmit the generated sentiment to a client computer.
In the preferred embodiment, the non-transitory computer-readable instructions further generate one or more graphical representations of the result that is being generated by using both the rules-based method and automatic method simultaneously.
In an embodiment, the non-transitory computer-readable instructions further perform the weightage analysis based on the severity of keywords included in the one or more queries.

In an embodiment, to identify the context of the specific word different types of classifier models are being used including, but is not limited to, naive bayes, logistic regression, support vector machines, and neural networks.
In an embodiment, the method to determine sentiment related to a particular brand is used different industries including, but is not limited to, a fashion industry, a, tourism industry, hotel industries, and food industry. In the preferred embodiment, the method to determine sentiment related to a particular brand is used in tourism industry.
In an embodiment, the present invention relates a method to determine sentiment related to a particular brand. A processor of one or more analytic servers executes a set of methods. The method includes
A rule-based method, the method having
a set of human-crafted rules is created;
the set of human-crafted rules identify subjectivity, polarity, context, and the subject of an opinion about a brand, from the retrieved data;
the non-transitory computer-readable instructions are developed base on the set of human-crafted rules;
the non-transitory computer-readable instructions are feed into the analytic server database of the one or more analytic servers;
further, the processor executes the non-transitory computer-readable instructions to identify subjectivity, polarity, context, and the subject of an opinion about a brand, from the retrieved data;
thus, sentiment related to the brand is determined based on subjectivity, polarity, context, and the subject of an opinion about the brand.
In an embodiment, the non-transitory computer-readable instructions develop based on a set of human-crafted rules perform the sentiment analysis using

different computational techniques selected from stemming, tokenization, part-of-speech tagging and parsing, lexicons.
In an embodiment, the non-transitory computer-readable instructions further perform at least one of a live search and trend-based search based on the one or more queries.
An automatic method, the methods having
the processing unit executes computer-readable instructions to extract data related to a brand;
data are refined and labeled, thus creating a data set of specific word and context of the specific word;
the refined data set is fed into a classifier model to train the classifier model to identify the context of the specific word;
the classifier model is further tested and optimized;
the trained classifier model is further stored in into the analytic server database of the one or more analytic servers;
further, the processor feed data into the trained classifier model to identify the context of the specific word;
thus, sentiment related to the brand is determined based on the identified context of the specific word;
wherein, the processor uses the results of both the rules-based method and automatic method to accurately determine the sentiment related to the brand and the further sentiment is categorization as negative, positive, and neutral.
wherein, the computing server is connected to an external internet server to retrieve data for brand analysis.
In an embodiment, the set of instructions further transmit the generated sentiment to the one or more client computers.

In the preferred embodiment, the non-transitory computer-readable instructions further generate one or more graphical representations of the result that is being generated by using both the rules-based method and automatic method simultaneously.
In an embodiment, the non-transitory computer-readable instructions further perform the weightage analysis based on the severity of keywords included in the one or more queries.
In an embodiment, to identify the context of the specific word different types of classifier models are being used including, but is not limited to, naive bayes, logistic regression, support vector machines, and neural networks.
In an embodiment, the method to determine sentiment related to a particular brand is used different industries including, but is not limited to, a fashion industry, a, tourism industry, hotel industries, and food industry. In the preferred embodiment, the method to determine sentiment related to a particular brand is used in tourism industry.
Further objectives, advantages, and features of the present invention will become apparent from the detailed description provided herein below, in which various embodiments of the disclosed present invention are illustrated by way of example and appropriate reference to accompanying drawings. Those skilled in the art to which the present invention pertains may make modifications resulting in other embodiments employing principles of the present invention without departing from its spirit or characteristics, particularly upon considering the foregoing teachings. Accordingly, the described embodiments are to be considered in all respects only as illustrative, and not restrictive, and the scope of the present invention is, therefore, indicated by the appended claims rather than by the foregoing description or drawings. Consequently, while the present invention has been described regarding particular embodiments, modifications of structure, sequence, materials and the like apparent to those skilled in the art still fall within the scope of the invention as claimed by the applicant.

I/WE CLAIMS

1. A system(lOO) for brand analytics, the system(lOO) comprising:
an at least one computing server(102), wherein each of the at least one computing server(102) having
an analytic server database(104), the analytic server database(104) stores non-transitory computer-readable instructions and a machine learning model,
a processor(106), the non-transitory computer-readable instructions containing a set of instructions configured to instruct the processor(106) to perform sentiment analysis related to a particular brand by using the machine learning model and set of human-crafted rules, and generate a result by categorizing the sentiment related to a particular brand;
an at least one of a client device(108), the at least one of a client device(108) is connected to the at least one computing server(102), wherein the set of instructions further transmit the generated sentiment to at least one of a client device(108);
wherein the context is identified out of the retrieved data based on contextual analysis, thus sentiment is determined from the context and further sentiment is categorization as negative, positive and neutral,
wherein the non-transitory computer-readable instructions further transmit the generated sentiment result to the at least one of a client device(108).
2. The system(lOO) as claimed in claim 1, the at least one computing server(102) is selected from a desktop computer, laptop, tab and smartphone, cluster computers.
3. The system(lOO) as claimed in claim 1, the at least one computing server(102) is connected to an external internet sever(l 10) to retrieve data for brand analysis.

4. The system(lOO) as claimed in claim 1, wherein to determine sentiment related to a particular brand the processor(106) executes set of methods, the method having
a rule-based method, the method having
a set of human-crafted rules is created,
the set of human-crafted rules identify subjectivity, polarity, context, and the subject of an opinion about a brand, from the retrieved data,
the non-transitory computer-readable instructions are developed base on the set of human-crafted rules,
the non-transitory computer-readable instructions are feed into the analytic server database(104) of the at least one computing server(102),
further, the processor(106) executes the non-transitory computer-readable instructions to identify subjectivity, polarity, context, and the subject of an opinion about a brand, from the retrieved data
thus, sentiment related to the brand is determined based on subjectivity, polarity, context, and the subject of an opinion about the brand;
an automatic method, the methods having
the processing unit(106) executes computer-readable instructions to extract data related to a brand,
data are refined and labeled, thus creating a data set of specific word and context of the specific word,
the refined data set is fed into a classifier model to train the classifier model to identify the context of the specific word,
the classifier model is further tested and optimized,
the trained classifier model is further stored in the analytic server database(104) of the at least one computing server(102),

further, the processor(106) feed data into the trained classifier model to identify the context of the specific word,
thus, sentiment related to the brand is determined based on the identified context of the specific word;
wherein, the processor(106) uses the results of both the rules-based method and automatic method to accurately determine the sentiment related to the brand and the further sentiment is categorization as negative, positive, and neutral,
wherein, the at least one computing server(102) is connected to an external internet server (110) to retrieve data for brand analysis.
5. The method of claim 4, wherein the non-transitory computer-readable instructions develop based on a set of human-crafted rules performs the sentiment analysis using different computational techniques selected from stemming, tokenization, part-of-speech tagging and parsing, lexicons.
5. The method of claim 4, wherein the non-transitory computer-readable instructions further perform at least one of a live search and trend-based search based on the one or more queries.
7. The method of claim 4, wherein the non-transitory computer-readable instructions further generate one or more graphical representations of the result that is being generated by using both the rules-based method and automatic method simultaneously.
8. The method of claim 4, wherein the non-transitory computer-readable instructions further perform the weightage analysis based on the severity of keywords included in the one or more queries.
9. The method of claim 4, wherein, to identify the context of the specific word different types of classifier models are being used selected from naive bayes, logistic regression, support vector machines, and neural networks.

10. The method of claim 4, wherein, the method to determine sentiment related to a particular brand is used a, tourism industry.