TABLE OF CONTENTS
Declaration …………………………………………………………………………………………………………2
Abstract ……………………………………………………………………………………………………………..4
Objectives ………………………………………………………………………………………………………….5
Definitions ………………………………………………………………………………………………………….7
List of Tables ………………………………………………………………………………………………………8
List of Figures …………………………………………………………………………………………………….9
1.Introduction ……………………………………………………………………………………………………10
2.0 Literature Review ……………………………………………………………………………………….. 11
2.1 Structured and Unstructured data ………………………………………………………………….. 13
2.2 Terminology ………………………………………………………………………………………………. 13
2.3 Fundamentals of Sentiment Analysis ……………………………………………………………. 14
2.3.1 Semantic Orientation ……………………………………………………………………………….. 14
2.3.2 Sentiment Classification …………………………………………………………………………….15
2.4 Document – level approach to Sentiment Analysis:Unsupervised ………………………15
2.5 Document – level approach to Sentiment Analysis:Machine Learning……………….. 18
2.6 Other related Document Level Approaches ……………………………………………………..20
2.7 Sentence level ………………………………………………………………………………………………21
2.7.1Subjectivity Classification ………………………………………………………………………….. 21
2.7.2 Sentence level Classification methods ………………………………………………………… 22
2.8 Feature based Opinion Summarization …….. ……………………………………………….. 26
2.9 Summary …………………………………………………………………………………………………… 27
3 Methodology ………………………………………………………………………………………………… 28
3.1 Dataset ………………………………………………………………………………………………………. 28
3.2.1 P.O.STagging …………………………………………………………………………………………… 28
3.3 APIs ………………………………………………………………………………………………………….. 29
3.3.1YahooBossAPI …………………………………………………………………………………………. 29
3.3.2 Google AJAX Search API …………………………………………………………………………. 29
3.3.3 Google WEB 1T grams …………………………………………………………………………….. 30
3.3.4 Yahoo Ordered Search ………………………………………………………………………………. 32
3.3.5 Google Ordered Search ………………………………………………………………………………33
3.4 Exalead Search Engine ………………………………………………………………………………….36
4.0Experiment …………………………………………………………………………………………………. 37
4.1 Summary of results ……………………………………………………………………………………… 39
5.0Conclusion ………………………………………………………………………………………………….. 42
Bibliography ……………………………………………………………………………………………………. 53
7
CHAPTER ONE
. Introduction: Overview
Sentiment analysis is a technique that allows computers analyse texts from comments,
blogs, review aggregation websites and various types of social media to determine
opinions about products and services or a domain such as movie reviews. The aim is to
extract opinions, emotions and sentiments in the text. The sentiment of the text is then
categorized into positive or negative, recommended (thumbs up) or not recommended
(thumbs down) or scaled into 1 to 5 star categories. Amazon1 for instance, use star
ratings.
Sentiment analysis application areas are for example, a brand tracking what
bloggers are saying about a new product or service. As more consumers make purchases
online, this potential customers go through reviews left by other customers who have
purchased a similar product often basing their decision to buy on the ratings. A five star
product is more likely to be preferred over a 2 star product. Tracking this opinions is in
the interest of the product manufacturer as well.
However, the application of sentiment analysis is not restricted only to consumer
goods sector. Sentiment analysis tasks could be applied to get political opinions of
anybody. It could be applied to newspapers stories or editorials. This when applied to
different news sources could help highlight different opinion holders in media. This
knowledge can then be used for targeted adverts. Also, businesses can track new product
perception, detect flames and general brand perception.
Www.amazon.com/uk
IF YOU CAN'T FIND YOUR TOPIC, CLICK HERE TO HIRE A WRITER»
