Brahim Dib, Fahd Kalloubi, E. Nfaoui, Abdelhak Boulaalam
{"title":"Leveraging topic feature for followee recommendation on Twitter network","authors":"Brahim Dib, Fahd Kalloubi, E. Nfaoui, Abdelhak Boulaalam","doi":"10.1109/ISCV49265.2020.9204041","DOIUrl":null,"url":null,"abstract":"With the fast growth of the Twitter network, users are overwhelmed by the huge amount of information, which is shared via the follower/followee social network, to overcome this problem, finding like-minded users becomes a very important task. Thus, a system to assist users in such a task is recommended. In this paper, we propose a followee recommendation system by leveraging the topic feature, for topic modeling, and the follower/followee topology, searching for similar users to recommend, based on topic similarities. To show the effectiveness of our approach, we evaluate it using a dataset ingathered from the Twitter platform. The experiment results indicate that our model outperforms the lexical-based [reference?] approach and semantic-based approach [reference?], achieving a recall value of more than 23% on recommending 10 followees, proving that dealing with users’ topics of interest in microblogging websites content is more efficient than semantic and lexical features.","PeriodicalId":313743,"journal":{"name":"2020 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 International Conference on Intelligent Systems and Computer Vision (ISCV)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISCV49265.2020.9204041","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
With the fast growth of the Twitter network, users are overwhelmed by the huge amount of information, which is shared via the follower/followee social network, to overcome this problem, finding like-minded users becomes a very important task. Thus, a system to assist users in such a task is recommended. In this paper, we propose a followee recommendation system by leveraging the topic feature, for topic modeling, and the follower/followee topology, searching for similar users to recommend, based on topic similarities. To show the effectiveness of our approach, we evaluate it using a dataset ingathered from the Twitter platform. The experiment results indicate that our model outperforms the lexical-based [reference?] approach and semantic-based approach [reference?], achieving a recall value of more than 23% on recommending 10 followees, proving that dealing with users’ topics of interest in microblogging websites content is more efficient than semantic and lexical features.