Introduction
Introduction
Influence is a complex and subtle force that governs the dynamics of social networks as well as the behaviors of involved users. Understanding the influence can benefit various applications such as viral marketing, personalized recommendation, and information retrieval.
We validate the approach on three different genres of data sets: Twitter, Digg, and citation networks. Qualitatively, our approach can discover interesting influence patterns in heterogeneous networks. Quantitatively, the learned topic-level influence can greatly improve the accuracy of user behavior prediction.
Citation Data
Citation Data
We crawled the citation data of about 1000 documents from the Internet on several specific topics, e.g., “topic models”, “sentiment analysis”, “association rule mining”, “privacy security” and etc. We manually labeled the influence strength from cited papers to citing papers in the data to test the influence strength prediction performance of our approach.
The data and code can be downloaded here.
Twitter and Digg Data
Twitter and Digg Data
Beside the citation data, we also mined the influence between the users on Twitter and Digg social networks.
We crawled twitter data from Twitter website and selected several topics for testing. The source data can be downloaded here. The parse code can be downloaded here.
The digg data are supllied by Yu-Ru Lin, which can be downloaded here.
References
References
If you use this data set for research, please cite one of the following papers:
- Lu Liu, Jie Tang, Jiawei Han, Meng Jiang, and Shiqiang Yang. Mining Topic-Level Influence in Heterogeneous Networks. In Proceedings of the Nineteenth Conference on Information and Knowledge Management (CIKM'2010). (full paper) [PDF]
- Jie Tang, Jimeng Sun, Chi Wang, and Zi Yang. Social Influence Analysis in Large-scale Networks. In Proceedings of the Fifteenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (SIGKDD'2009). pp. 807-816. [PDF] [Slides] [Data]