ABSTRACT

CHAPTER ONE

INTRODUCTION

1. 1. Background of the Study

In the internet age, whether a book in an online web-store is worth reading depends on the review that an individual sees on the book comment reviews. Online user’s comments play an important role in helping individuals to make this important decision. With the rapid development of electronic-commerce websites, people's lives have become more convenient in purchasing goods remotely online; for quite some time now, a lot of data on book reviews has been produced as user comments reviews increase in online book stores. The sentiment polarity analysis of such data can help form a win-win relationship for both businessmen and users. Merchants can find out the quality of books through the comments on them and improve the quality of their stores. Users can judge the contents of the books according to the comments. Therefore, the sentiment analysis has an important academic research value and practical application value. Text sentiment analysis refers to the process of analyzing and collating texts with personal subjective opinions, which involves text categorization and information extraction etc. (Zhao et al., 2010).

Sentiment analysis as a new field of data mining has an important academic research value and practical application value. Web user comment mining is an important research field of sentiment analysis. In the aspect of sentiment analysis, English texts sentiment analyses have been greatly developed. The text information, especially the analysis of sentiment tendency on online comment texts has been made a significant breakthrough. At present the accuracy of sentiment tendency analysis based on the online comments has reached more than 90% (Srujan et al., 2018).

Human beings are pretty good at determining sentiment. We can look at a review and immediately comprehend if it is negative or positive. Companies across the world have implemented machine learning to do sentiment analysis automatically. It is useful for gaining insight into customer opinions. After analyzing the reviews, we can identify customer’s opinion about the product (Tripathy et al., 2015). By sentiment analysis, companies can build recommendation systems or better targeted marketing campaigns. The complexity in sentiment analysis includes removing noisy data from raw dataset, selecting suitable features for representation and choosing appropriate classifier (Srujan et al., 2018).  

1.2     Statement of the Problem

Advancement of web based technologies has led to storage of abundant information on internet. Looking at the e-commerce prospective, all major products are available on internet on various reputed websites such as Amazon, Flipkart, Google etc. These websites contain detailed description of the products including their price, availability, functionality, customer ratings, feedbacks, blogs etc. A new buyer can utilize these digital words of mouth to draft a viewpoint about a specific product. For example, a book is given ratings by various consumers who have previously bought and read it. Collectively, these reviews may be used to form a firm opinion about how is the book, what genre of people like or do not like it, if it is better than its prequel etc. For instance, a given book XYZ may have around 500 reviews where review stars range from one to five and the textual content may vary from “Very nice” to “Not Worth reading”. One option is that readers can go through all the provided reviews and analyze whether they should read the book or not based upon analysis done through those reviews. This process of opinion formation is clearly time consuming and tiresome especially if the number of reviews is large and diverse in nature. Alternatively, automated machine learning computational techniques like Sentiment Analysis or Data Mining can be used for the purpose of opinion building and determining the sentiment direction of an online review text provided on the website by other readers of the book.

1.3     Aim and Objectives of the Study

The aim of this research work is to design and implement an automated book review analysis system that will be used to evaluate or rate a book based on the comments reviews or opinions of individuals who have read the book before. It will also facilitate the individual with parameters covering all the aspects required by the user to choose a suitable book according to his needs and requirement standards.

The objectives of the study are to;

i. Design a book review analysis system using Unified Model Language (UML) tools.

ii. Implement the system in above using a data mining (sentiment analysis algorithm) in an online platform using Hypertext Processor (PHP) programming language.

iii. Test the system implemented in (ii) for performance.

1.4     Significance of the Study

This study will serve as a platform to mitigate the chances of an individual buying a book which does not actually meets his demands or expectations and also stand against fraudulent authors who writes substandard books with captivating prefaces to come to nut.  Furthermore, this will also serve to help individuals to make better choice of deciding which book to buy and which not to.

The software is relevant in the following ways:

1. The designed software will aid in carrying out book ratings based on users comment reviews.
2. The designed software will aid merchants to find out the quality of books on the web-stores via readers’ comments reviews on them and improve the quality of books on their web-stores
3. The system will serve as a conduit for further research by scholars and academicians.
4. The designed system will be useful to individuals in times of making quick decision on which book to read or buy.
5. The designed software will be useful to book authors to know the opinion of their readers with regards to the quality of their books.
6. The designed software will also be relevant to any individual or agency which will like to carry out a survey on a book to know opinion of the society towards the book.

1.5     Scope of the Study

This research work covers the design and implementation of an automated book review analysis system using data mining on users comment reviews with special focus to online books.

1.6 Definition of Terms

Analysis: Analysis is the process of breaking a complex topic or substance into smaller parts in order to gain a better understanding of it.

Book: A book is a handwritten or printed work of fiction or nonfiction, usually on sheets of paper fastened or bound together within covers.

Data analysis: This is a process of inspecting, cleansing, transforming and modeling data with the goal of discovering useful information, informing conclusion and supporting decision-making.

Data Mining Algorithm: It is a set of heuristics and calculations that creates a model from data. To create a model, the algorithm first analyzes the data you provide, looking for specific types of patterns or trends.

Data Mining: Data mining is the process of discovering patterns in large data sets involving methods at the intersection of machine learning, statistics, and database systems

Dataset: A data set is a collection of data. In the case of tabular data, a data set corresponds to one or more database tables, where every column of a table represents a particular variable, and each row corresponds to a given record of the data set in question.

Decision-Making: the action or process of making important decisions.

Evaluation: this is a systematic determination of a subject's merit, worth and significance, using criteria governed by a set of standards.

Feedback: information about reactions to a product, a person's performance of a task, etc. which is used as a basis for improvement.

Fraudulent: obtained, done by, or involving deception, especially criminal deception.

Internet: Internet is a global system of interconnected computer networks that use the standard Internet protocol suite (TCP/IP) to serve billions of users worldwide. It is also known as the network of networks.

Noisy Data: Noisy data is data that is corrupted, or distorted, or has a low Signal-to-Noise Ratio. Improper procedures to subtract out the noise in data can lead to a false sense of accuracy or false conclusions.

Opinion Mining: this is a type of natural language processing for tracking the mood of the public about a particular entity or product. Opinion mining, which is also called sentiment analysis, involves building a system to collect and categorize opinions about a product or services.

Opinion: An opinion can be defined as a view or judgment formed about something, not necessarily based on fact or knowledge..

Patronize: frequent (a shop, restaurant, or other establishment) as a customer.

Personal Subjective Opinion: This refers to personal perspectives, feelings, or opinions entering a decision making process.

Professional Critic: A professional critic is one who communicates an assessment and an opinion of various forms of creative works such as art, literature, music, cinema, theatre, fashion, architecture, and food. 

Publication: To publish is to make content available to the general public. While specific use of the term may vary among countries, it is usually applied to text, images, or other audio-visual content, including paper. The word publication means the act of publishing, and also refers to any printed copies

Raw Dataset: is a dataset that has not been processed for use.

Review: A review is an evaluation of a publication, service, or company such as a movie, video game, musical composition, book; a piece of hardware like a car, home appliance, or computer; or an event or performance, such as a live music concert, play, musical theater show, dance show, or art exhibition.

Sentiment Analysis: Sentiment analysis refers to the use of natural language processing, text analysis, computational linguistics, and biometrics to systematically identify, extract, quantify, and study affective states and subjective information. 

Sentiment Polarity Analysis: This is the classification of a textual sentiment polarity into positive, negative or Neutral.

Sentiment Polarity: Refers to identifying sentiment orientation (positive, neutral, and negative) in written or spoken language. Other types of sentiment analysis include fine-grained sentiment analysis which provides more precision in the level of polarity (e.g. very positive, positive, neutral, negative, and very negative) and emotion analysis which aims to identify emotions in expressions (e.g. happiness, sadness, frustration, surprise, etc).

Sentiment Tendency Analysis: This is the analysis of the polarity probability of a text sentiment to be negative, positive or Neutral.

Society: is a group of individuals involved in persistent social interaction, or a large social group sharing the same spatial or social territory, typically subject to the same political authority and dominant cultural expectations

Software: These are set of instructions that are designed to solve a specific problem. Software is made up of data and instructions. There are two categories of software; System software and Application software.

System: A system is a set of detailed methods, procedures and routines created to carry out a specific activity, perform a duty, or solve a problem

Text Sentiment Analysis: is a text analysis method that detects polarity (e.g. a positive or negative opinion) within text, whether a whole document, paragraph, sentence, or clause.

Unified Modeling Language: The Unified Modeling Language is a general-purpose, developmental, modeling language in the field of software engineering that is intended to provide a standard way to visualize the design of a system.

Web: The Web is basically a system of Internet servers that support specially formatted documents.