상세정보
학술지
Predicting the Lifespan and Retweet Times of Tweets Based on Multiple Feature Analysis
- 발행일
- 201406
- 출처
- ETRI Journal, v.36 no.3, pp.418-428
- ISSN
- 1225-6463
- 출판사
- 한국전자통신연구원 (ETRI)
- 협약과제
- 14MS4400, 휴먼 지식증강 서비스를 위한 지능진화형 Wise QA 플랫폼 기술 개발, 박상규
- 초록
- In social network services, such as Facebook, Google+, Twitter, and certain postings attract more people than others. In this paper, we propose a novel method for predicting the lifespan and retweet times of tweets, the latter being a proxy for measuring the popularity of a tweet. We extract information from retweet graphs, such as posting times; and social, local, and content features, so as to construct prediction knowledge bases. Tweets with a similar topic, retweet pattern, and properties are sequentially extracted from the knowledge base and then used to make a prediction. To evaluate the performance of our model, we collected tweets on Twitter from June 2012 to October 2012. We compared our model with conventional models according to the prediction goal. For the lifespan prediction of a tweet, our model can reduce the time tolerance of a tweet lifespan by about four hours, compared with conventional models. In terms of prediction of the retweet times, our model achieved a significantly outstanding precision of about 50%, which is much higher than two of the conventional models showing a precision of around 30% and 20%, respectively. © 2014 ETRI.
- KSP 제안 키워드
- Content features, Feature Analysis, Knowledge bases, Lifespan prediction, Posting times, Social Network Service, conventional model, knowledge base, multiple features, novel method, social network(SN)