Opinion Mining and Information Retrieval: Techniques for E-Commerce

Opinion Mining and Information Retrieval: Techniques for E-Commerce

Shishir K. Shandilya, Suresh Jain
DOI: 10.4018/978-1-61692-857-5.ch030
OnDemand:
(Individual Chapters)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

The explosive increase in Internet usage has attracted technologies for automatically mining the user-generated contents (UGC) from Web documents. These UGC-rich resources have raised new opportunities and challenges to carry out the opinion extraction and mining tasks for opinion summaries. The technology of opinion extraction allows users to retrieve and analyze people’s opinions scattered over Web documents. Opinion mining is a process which is concerned with the opinions generated by the consumers about the product. Opinion Mining aims at understanding, extraction and classification of opinions scattered in unstructured text of online resources. The search engines performs well when one wants to know about any product before purchase, but the filtering and analysis of search results often complex and time-consuming. This generated the need of intelligent technologies which could process these unstructured online text documents through automatic classification, concept recognition, text summarization, etc. These tools are based on traditional natural language techniques, statistical analysis, and machine learning techniques. Automatic knowledge extraction over large text collections like Internet has been a challenging task due to many constraints such as needs of large annotated training data, requirement of extensive manual processing of data, and huge amount of domain-specific terms. Ambient Intelligence (AmI) in wed-enabled technologies supports and promotes the intelligent e-commerce services to enable the provision of personalized, self-configurable, and intuitive applications for facilitating UGC knowledge for buying confidence. In this chapter, we will discuss various approaches of Opinion Mining which combines Ambient Intelligence, Natural Language Processing and Machine Learning methods based on textual and grammatical clues.
Chapter Preview
Top

Introduction

Based on the convergence of ubiquitous computing, ubiquitous communication and intelligent user-friendly interfaces, Ambient Intelligence is future of E-commerce. Ubiquitous Computing deals with the integration of microchips into everyday objects while Ubiquitous Communication facilitates these objects to communicate with each other and intelligent user interfaces provides the control to the users to control and interact with the AmI environment effectively. The present global market scenario facilitates and promotes the e-commerce and e-business activities, making them a strong catalyst for economic development. The rapid and remarkable development in the field of information and communication technologies has increased the consumer participation and customization in almost every business. Users now actively write their experiences, choices, and recommendations on blogs, discussion boards or websites etc. Product reviews exist in various formats on the Internet. Like the websites dedicated to a specific type of product (such as TV or Fridge), sites for newspapers and magazines that may feature reviews (like Consumer Reports), and sites that collects professional or user reviews in specific domains (like codeguru.com in computers), or the broader domains (wikipedia.com and yahoo.com). The business community has welcomed this change in market and dealing with it perfectly by strategically positioning their products or services. The company determines the upcoming opportunities and work for them with appropriate strategies and policies while exploiting the latest technologies, which is encouraging the use e-commerce technologies in advertising, marketing and promotion. The Internet is used as a medium for enhanced customer satisfaction. The companies are providing more detailed information about the product or service to increase the trust and determination of potential buyers.

The recent developments in web technologies have increased the acceptability and reliability ratio of e-commerce. Customers are now relying more trustfully on the information of web which plays remarkable role in their decisions of purchase. Customers now tend to search the web thoroughly before any purchase/decision. They prefer to know the opinions and suggestions of existing customers to portray the image of product or service accordingly. Fast technological advancements in digitization of user-generated content, natural language processing and web mining have paved a way for mining directly the opinions scattered over web about a particular product/service. This requires fast and efficient procedure which can also represent the results in simple and lucid manner. Using such technologies makes the e-commerce competitive enough to provide greater satisfaction to the potential customers.

The business strategies and future action plans relies greatly on the consumer’s opinions and experiences who have used the product at least once. As the businesses are rapidly transferring over web, so the opinions and suggestions are. The user-generated text is growing enormously, making it prospective area of mining. This needs to automatically extract and analyze personal opinions from web documents. Such technologies can be an alternative to conventional questionnaire-based surveys and would also benefit Web users who seek reviews on certain consumer products of their interest.

Key Terms in this Chapter

Sentiment Classification: Given a set of evaluative documents D, it determines whether each document d ? D expresses a positive or negative opinion (or sentiment) on an object.

Targeted Opinion Detection: In the targeted opinion detection stage, opinion detection ventured outside the relatively structured review data of the Web to consider associations between opinions and their corresponding topics.

Point-wise Mutual Information (PMI): It is a measure of association used in information theory and statistics. The PMI of a pair of outcomes of random variables quantifies the discrepancy between the probabilities of their coincidences.

Sentiment Analysis: It aims to determine the attitude of a writer on the topic. The attitude may be their judgment or evaluation, or the intended emotional communication on the topic.

User Generated Content: It refers to the content produced by the consumers on various types of media like forum, blogs, discussion boards, and social networking sites.

Opinion Mining: Opinion mining is a process of information retrieval, which is concerned not with the topic, a document is about, but with the opinion it expresses.

Semantic Orientation: The semantic orientation of an opinion on a feature f states whether the opinion is positive, negative or neutral.

Complete Chapter List

Search this Book:
Reset