期刊
NEW GENERATION COMPUTING
卷 39, 期 1, 页码 199-229出版社
SPRINGER
DOI: 10.1007/s00354-020-00103-1
关键词
Sentiment analysis; Knowledge engineering; Conceptual similarity; Knowledge graph; Disambiguation
资金
- CONACYT
- JSPS KAKENHI [JP17H01789]
A knowledge-based methodology for sentiment analysis on social networks was proposed, utilizing knowledge graphs, similarity measures, graph theory algorithms, and a disambiguation process. Results were compared with data from Twitter and Amazon reviews, showing efficiency and advantages. Analysis was conducted to find best classification performance using polarity, sentiment, and a polarity-sentiment hybrid, arguing for the benefit of using a disambiguation process in knowledge processing.
A knowledge-based methodology is proposed for sentiment analysis on social networks. The work was focused on semantic processing taking into account the content handling the public user's opinions as excerpts of knowledge. Our approach implements knowledge graphs, similarity measures, graph theory algorithms, and a disambiguation process. The results obtained were compared with data retrieved from Twitter and users' reviews in Amazon. We measured the efficiency of our contribution with precision, recall, and the F-measure, comparing it with the traditional method of looking up concepts in dictionaries which usually assign averages. Moreover, an analysis was carried out to find the best performance for the classification by using polarity, sentiment, and a polarity-sentiment hybrid. A study is presented for arguing the advantage of using a disambiguation process in knowledge processing. A visualization system presents the social graphs to display the sentiment information of each comment as well as the social structure and communications in the network.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据