Introduction to ReviewMiner
The ReviewMiner system, developed by Hongning Wang and team, utilizes Latent Aspect Rating Analysis to analyze review text data. It offers functionalities like keyword-based item retrieval and aspect-based review analysis. The system features a search-oriented interface, aspect-based item comparison, and personalized recommendation results.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
Introduction to ReviewMiner Hongning Wang Department of Computer Science University of Illinois at Urbana-Champaign wang296@Illinois.edu
Introduction ReviewMiner system is developed based on the work of Latent Aspect Rating Analysis published in KDD 10 and KDD 11 Hongning Wang, Yue Lu and Chengxiang Zhai. Latent Aspect Rating Analysis on Review Text Data: A Rating Regression Approach. The 16th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'2010), p783-792, 2010. Hongning Wang, Yue Lu and ChengXiang Zhai. Latent Aspect Rating Analysis without Aspect Keyword Supervision. The 17th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'2011), P618-626, 2011. http://timan100.cs.uiuc.edu:8080/ReviewMiner
Latent Aspect Rating Analysis Aspect Segmentation + Latent Rating Regression Reviews + overall ratings Aspect segments Term Weights 0.0 2.9 0.1 0.9 Aspect Rating Aspect Weight location:1 amazing:1 walk:1 anywhere:1 3.9 0.2 room:1 nicely:1 appointed:1 comfortable:1 0.1 1.7 0.1 3.9 2.1 1.2 1.7 2.2 0.6 0.2 4.8 nice:1 accommodating:1 smile:1 friendliness:1 attentiveness:1 5.8 0.6 Boot-stripping method Latent! http://timan100.cs.uiuc.edu:8080/ReviewMiner
Functionalities Keyword-based item retrieval E.g., search hotels by name, location, brand Aspect-based review analysis Segment review content into aspects Predict aspect ratings based on overall ratings and review text content Infer latent aspect weights the reviewer has put over the aspects when generating the review content Aspect-based item comparison Predicted aspect rating/weight based quantitative comparison Text content based qualitative comparsion http://timan100.cs.uiuc.edu:8080/ReviewMiner
A search-oriented interface User registration and profile panel Search vertical selection panel Trending searches Search box (keyword queries) http://timan100.cs.uiuc.edu:8080/ReviewMiner
Search result page Search box (keyword queries) Aspect-weight based user profile Spatial result display Personalized recommendation results Search result list http://timan100.cs.uiuc.edu:8080/ReviewMiner
Highlight, compare and find similar items Supported analysis functions: compare and find similar items regarding to user s selection Aspect highlights of the selected item http://timan100.cs.uiuc.edu:8080/ReviewMiner
Review analysis page Aspect-based item highlights Review meta-info: reviewers, date, aspect ratings Helpfulness vote Aspect-segmented review content http://timan100.cs.uiuc.edu:8080/ReviewMiner
Aspect-based opinion summarization Analysis type selection: text summary v.s. graphical chart summary. Text summary of aspects http://timan100.cs.uiuc.edu:8080/ReviewMiner
Aspect-based review analysis Analysis type selection: aspect ratings, aspect weights, aspect mentions and aspect summarization. Analysis result display panel (move mouse over the chart to find the text highlights) http://timan100.cs.uiuc.edu:8080/ReviewMiner
Aspect-based item comparison Analysis type selection: aspect ratings, aspect weights, aspect mentions and aspect summarization. Aspect selection panel Analysis result display panel (move mouse over the chart to find the text highlights) http://timan100.cs.uiuc.edu:8080/ReviewMiner
Comments More search verticals to be added Our solution of LARA is general and can be easily extended to multiple domains Restaurant reviews from Yelp.com and electric product reviews from amazon.com will be included soon Your valuable comments and suggestions Feel free to send them to wang296@Illinois.edu I am looking forward to further discussions and collaborations http://timan100.cs.uiuc.edu:8080/ReviewMiner
