Influence Diffusion Model Based on Semantic Orientation and its Application in Opinion Leader Identification

Abstract:

As the pivotal intermediary guiding public opinion in the interpersonal communication network, opinion leader’s discovery and identification have great social significance. Aiming at the existing problem of IDM models and its related model, this paper proposed a Influence diffusion model based on semantic orientation, which combines semantic understanding to reduce the diffusion of mendacious influence, analyzing text orientation to quantify the emotional intention, using reply structure to calculate diffused influence, then identifying the network opinion leaders. Experiments indicated that this method can improve the accuracy of opinion leader identification effectively.

• Periodical: Applied Mechanics and Materials (Volumes 571-572)
• Pages: 223-231
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.571-572.223
• Online since: June 2014
• Authors: Li Li Dong, Fan Rong Zhao*, Xiang Zhang, Yu Jie Zhu
• Keywords: IDM, Opinion Leader Identification, Semantic Comprehension, Sentiment Analysis

References

[1] Lazarsfield P et al. The People's Choice[M]. New York, Columbia University Press, (1948).

[2] Tao Wenzhao. Attach importance to Online Opinion Leaders[J]. Chinese Cadres Tribune. 2007(10): 27-29.

[3] Wang Jue, Zeng Jianping, Zhou Baohua, et al. Online Forum Opinion Leaders Discovering Method Based on Clustering Analysis[J]. Computer Engineering, 2011, 37(5): 44-46.

[4] Li F, Du T C. Who is talking? An ontology-based opinion leader identification framework for word-of-mouth marketing in online social blogs[J]. Decision Support Systems, 2011, 51(1): 190-197.

DOI: 10.1016/j.dss.2010.12.007

[5] Zhai Z, Xu H, Jia P. Identifying opinion leaders in BBS[C]/Web Intelligence and Intelligent Agent Technology, 2008. WI-IAT'08. IEEE/WIC/ACM International Conference on. IEEE, 2008, 3: 398-401.

DOI: 10.1109/wiiat.2008.37

[6] Matsumura N, Ohsawa Y, Ishizuka M. Influence diffusion model in text-based communication[J]. Transactions of the Japanese Society for Artificial Intelligence, 2002, 17: 259-267.

DOI: 10.1527/tjsai.17.259

[7] Ning Ma, Yijun Liu . SuperedgeRank algorithm and its application in identifying opinion leader of online public opinion supernetwork[J]. Expert Systems with Applications. 2014, 4(41): 1357- 1368.

DOI: 10.1016/j.eswa.2013.08.033

[8] Fan Xinghua, Zhao Jing, Fang Bingxing, et al. Influence Diffusion Probability Model and Utilizing It to Identify Network Opinion Leader[J]. Chinese Journal of Computers. 2013, 2(36): 360-367.

DOI: 10.3724/sp.j.1016.2013.00360

[9] Chen Ran. Methods and Principles about Online Forum Opinion Leaders Discovering[J]. Media Time. 2012(9): 33-36.

[10] Yu Hong. Research on the Opinion Leaders of Political BBS: An Case Study on Sino-Japan BBS of Strong Nation Forum[D]. Huazhong University of Science & Technology. (2007).

[11] Liao Hao, Li Zhishu, Wang Qiuye, et al. Text feature word selection based on relationship between words. Computer Applications. 2007, 27(12): 3009-3012.

[12] Dong Lili, Zhao Fanrong, Zhang Xiang. Sentiment analysis of product reviews based on domain ontology and sentiment lexicon[J]. Computer Applications and Software. in press.

[13] Zou Juan, Zhou Jingye, Deng Cheng, et al. A new method for synonymous processing in feature word extraction of text categorization. Journal of Chinese Information processing. 2005, 19(6): 44-49.