ICTACT Journal on Soft Computing

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Sentiment Analysis Based on Fine Grained Feature Representation Of Domain Sentiment Dictionary


Affiliations
1 Department of Computer Applications, Kovai Kalaimagal College of Arts and Science, India., India
     

   Subscribe/Renew Journal


The era of information technology has grown tremendously over the decade. In the existing opinion mining technology, the response time and the accuracy are not up to the expectation. The sentiment analysis is not accurate in the traditional systems. The method failed to divide the opinion holder, tendency and the opinion object from the opinion given by the holder/user and it results to the failure in obtaining the overall report of the positive and negative feedbacks of the object. The proposed fine grained opinion mining can perform better in analyzing the holder, tendency, and expression from the statement. This accuracy of the proposed system is consistent in the case of large datasets such as reading the reviews of the customers and filters the positive and negative opinion in an accurate manner. The proposed system uses the external sentiment directory for comparing the opinion given by the user and predefined emotional data stored in the directory.

Keywords

Opinion Mining, Sentiment Analysis, Emotional Mining, Conditional Random Field, Machine Learning.
Subscription Login to verify subscription
User
Notifications
Font Size

  • P. Lazarsfeld and M. Berelson, “The People’s Choice: How the Vote Makes up his Mind in a Presidential Campaign”, Columbia: Columbia University Press, 1968.

  • N. Weissmana, “The Role of the Opinion Leader Research Process in Forming Policy Making for Improved Nutrition: Experience and Lesson Learned-in-Southeast”, Current Development in Nutrition, Vol. 4, No. 6, pp. 1-14, 2020.

  • Minaeians Duboise and Paquet Labellea, “Who to Trust on Social Media: How Opinion Leaders and Seekers Avoid Disinformation and Echo Chambers”, Social Media Society, Vol. 6, No. 2, pp. 1-13, 2020.

  • R. Rashottel, “Blackwell Cyclopedia of Sociology”, Choice Reviews Online, Vol. 44, No. 11, pp. 4434-4437, 2007.

  • Liu Jiacheng, Ma Tingcan and Yue Mingliang, “HHa Centrality Algorithm: A Complicated Network Node Sorting Algorithm Based on h Index and Ha Index”, Library and Information Work, Vol. 65, No. 20, pp. 92-100, 2015.

  • Li Xiao, Qu Yang and Li Hui, “User Importance Evaluation Method for Online Question Answering Platform based on User Relationship”, Computer Science, Vol. 47, No. 2, pp. 430-436, 2020.

  • Liu Jiaqi, Qi Jiayin and Chen Manyi, “Research on the Relationship between Opinion Leaders and Online Group Influence based on Social Network Analysis”, Information Science, Vol. 36, No. 11, pp. 138-145, 2018.

  • J.M. Kleinberg, “Authoritative Sources in a Hyperlink Environment”, Journal of the ACM, Vol. 46, No. 5, pp. 604- 632, 1999.

  • S. Brin and L. Page, “The Anatomy of a Large-Scale Hyper Textual Web Search Engine”, Computer Networks and ISDN Systems, Vol. 30, No. 1, pp. 107-117, 1998.

  • J.M. Kleinberg, “Hubs, Authorities, and Communities”, ACM Computing Surveys, Vol. 31, pp. 1-15, 1999.

  • Z. Zhai and P. Jia, “Identifying Pinion Leaders in BBS”, Proceedings of IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, pp. 398-401, 2008.

  • G. Amit “Discovering Leaders from Community Actions”, Proceedings of International Conference on Information and Knowledge Management, pp. 499-508, 2008.

  • M.F. Tsai and Z.L. Lin ZL, “Discovering Leaders from Social Network by Action Cascade”, Social Network Analysis and Mining, Vol. 4, No. 1, pp. 1-10, 2014.

  • S. Xiaodan and H. Koji, “Identifying Pinion Leaders in the Blogosphere”, Proceedings of ACM International Conference Information and Knowledge Management, pp. 971-974, 2007.

  • Y. Li, S, Ma and Y. Zhang, “An Improved Mix Framework for Opinion Leader Identification in Online Learning Communities”, Knowledge-Based Systems, Vol. 43, pp. 43- 51, 2013.

  • H. Zhou and C. Zhang, “Finding Leaders from Opinion Networks”, Proceedings of International Conference on Intelligence and Security Information, pp. 266-268, 2009.

  • X. Liu, Y. Wang and Y. Li, “Identifying Topic Experts and Topic Communities in the Blog Space”, Proceedings of International Conference on Database Systems for Advanced Applications, pp. 68-77, 2011.

  • Xia Lin, “Topology Structure Research and Opinion Leader Identifying in BBS”, Master Thesis, Department of Computer Science, Wuhan: Huazhong University of Science and Technology, pp. 1-123, 2011.

  • Duan Jiangjiao, Jianping Zeng and Banghui Luo, “Identification of Opinion Leaders based on User Clustering and Sentiment Analysis”, Proceedings of IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent A-gent Technologies, pp. 1-12, 2014


Abstract Views: 115

PDF Views: 0




  • Sentiment Analysis Based on Fine Grained Feature Representation Of Domain Sentiment Dictionary

Abstract Views: 115  |  PDF Views: 0

Authors

S. Gnanapriya
Department of Computer Applications, Kovai Kalaimagal College of Arts and Science, India., India

Abstract


The era of information technology has grown tremendously over the decade. In the existing opinion mining technology, the response time and the accuracy are not up to the expectation. The sentiment analysis is not accurate in the traditional systems. The method failed to divide the opinion holder, tendency and the opinion object from the opinion given by the holder/user and it results to the failure in obtaining the overall report of the positive and negative feedbacks of the object. The proposed fine grained opinion mining can perform better in analyzing the holder, tendency, and expression from the statement. This accuracy of the proposed system is consistent in the case of large datasets such as reading the reviews of the customers and filters the positive and negative opinion in an accurate manner. The proposed system uses the external sentiment directory for comparing the opinion given by the user and predefined emotional data stored in the directory.

Keywords


Opinion Mining, Sentiment Analysis, Emotional Mining, Conditional Random Field, Machine Learning.

References