Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/454581
Title: | Scalable collaborative filtering assisted recommendation using adaptive chronological brain storm optimized sentiment classification |
Researcher: | Poongothai M |
Guide(s): | Sangeetha M |
Keywords: | Engineering and Technology Computer Science Computer Science Information Systems chronological Brain storm optimization sentiment classification |
University: | Anna University |
Completed Date: | 2022 |
Abstract: | Recommendation Systems (RS) are such important intelligent systems newlinethat have a prominent place in providing personalized ideas and similar newlinematters to users based on their past historical data. Sentiment Analysis (SA) is newlineapplied to stimulate the performance of RS. SA is the means of extracting newlineemotions, attitudes and opinions of persons in social media reviews, and then newlineclassifying them relying on the polarity of textual data present in the reviews. newlineThe major intention as per sentiment classification is to decide whether the newlinespecific document contains negative (-ve) or positive (+ve) nuance. The newlineprocess of sentiment classification is widely utilized by business newlineestablishments to analyze feedback on their products/services and accordingly newlineimprovise on their offerings. With the explosion of digital social networking newlineplatforms, the information available online has grown exponentially, and newlinetraditional techniques failed to acquire and process user attitudes reasonably newlinewell. Hence, to handle large volume of scalable data and providing newlinerecommendation based on the user and the item (collaborative)characteristic newlinethis research is focused on developing a scalable and optimal learning-based newlineclassification technique using MapReduce for the process of sentiment newlineclassification and then developing a cluster based improved, adaptive CF-RS newlinebased on sentiment analysis for handling large set of movie database with newlineimproved prediction quality by tackling sparsity. This helps in better newlineprediction of services in less time. newlineThe principle intention of this research is to come about a model newline |
Pagination: | xxiii, 153p. |
URI: | http://hdl.handle.net/10603/454581 |
Appears in Departments: | Faculty of Information and Communication Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
01_title.pdf | Attached File | 10.31 kB | Adobe PDF | View/Open |
02_prelim pages.pdf | 19.44 kB | Adobe PDF | View/Open | |
03_content.pdf | 198.39 kB | Adobe PDF | View/Open | |
04_abstract.pdf | 107.22 kB | Adobe PDF | View/Open | |
05_chapter 1.pdf | 318.18 kB | Adobe PDF | View/Open | |
06_chapter 2.pdf | 181.74 kB | Adobe PDF | View/Open | |
07_chapter 3.pdf | 658.47 kB | Adobe PDF | View/Open | |
08_chapter 4.pdf | 580.59 kB | Adobe PDF | View/Open | |
09_chapter 5.pdf | 560.01 kB | Adobe PDF | View/Open | |
10_chapter 6.pdf | 397.65 kB | Adobe PDF | View/Open | |
11_annexures.pdf | 129.65 kB | Adobe PDF | View/Open | |
80_recommendation.pdf | 42.31 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: