Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/434743
Title: | Unstructured data analytics of social network reviews using sentiment analysis |
Researcher: | Bairavel S |
Guide(s): | Krishnamurthy M |
Keywords: | Engineering and Technology Computer Science Computer Science Information Systems Data Analytics Social Network Reviews Unstructured Data Analytics Sentiment Analysis User Generated Content |
University: | Anna University |
Completed Date: | 2021 |
Abstract: | The rise of web 2.0 leads to a massive generation of User Generated Content (UGC) with different networks. UGC may be used and integrated to improve the performance of multimedia applications such as search engines, annotation, marketing, and recommendation by providing real-time semantic modeling. One of the prominent multimedia applications that have the researcher s interest and connect directly with the lives of individuals is the intelligent Travel Recommendation System (TRS). According to the World Travel and Tourism Council s statistics, the present generation heavily relies on information offered by various tourist websites before visiting a certain travel location throughout the world. Online travel services, like TripAdvisor, enable visitors to share views of the various destinations they have been in recent years. Due to the rapid development of these websites, a large amount of unstructured information prohibits users from quickly and effectively discovering desired tourist destinations. Different travel agencies are mostly focusing on personalized TRS to maximize their profits. The personalized TRS mainly exploits the user s preferences to provide the appropriate recommendations. There is a different sentiment associated with each review and it mainly specifies the user s preferences. In user attraction, the sentiment is either positive or negative. To design a context-aware TRS, sentimental analysis techniques play a major role. This thesis presents two sentimental analysis models that focus on both single and multiple modalities to offer improved performance with higher accuracy. newline newline |
Pagination: | xvii, 145p. |
URI: | http://hdl.handle.net/10603/434743 |
Appears in Departments: | Faculty of Information and Communication Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
01_title.pdf | Attached File | 25.87 kB | Adobe PDF | View/Open |
02_prelim pages.pdf | 492.39 kB | Adobe PDF | View/Open | |
03_content.pdf | 35.33 kB | Adobe PDF | View/Open | |
04_abstract.pdf | 132.56 kB | Adobe PDF | View/Open | |
05_chapter 1.pdf | 496.96 kB | Adobe PDF | View/Open | |
06_chapter 2.pdf | 385.02 kB | Adobe PDF | View/Open | |
07_chapter 3.pdf | 240.75 kB | Adobe PDF | View/Open | |
08_chapter 4.pdf | 857.41 kB | Adobe PDF | View/Open | |
09_chapter 5.pdf | 1.46 MB | Adobe PDF | View/Open | |
10_chapter 6.pdf | 255.54 kB | Adobe PDF | View/Open | |
11_annexures.pdf | 136.84 kB | Adobe PDF | View/Open | |
80_recommendation.pdf | 53.21 kB | Adobe PDF | View/Open |
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: