ENSEMBLE OF TWITTER FEATURE SETS AND CLASSIFICATION ALGORITHMS FOR SENTIMENT CLASSIFICATION

Anu S, Kalaiselvi. M

Abstract


Sentiment analysis of Twitter information. Sentiment or utilizes the Naive Bayes Classifier to classify Tweets into positive, negative neutral, or negation we have a tendency to gift experimental analysis of our Live Review Twitter dataset and classification results, Sentiment Analysis could be a task to spot Associate in Nursing text as comments, reviews or message. The similarity between user rating schedules is employed to represent social rating behavior similarity. The factor of social rating behaviour diffusion is planned to deep perceive users’ rating behaviors. we have a tendency to explore the user’s social circle, and split the social network into 3 parts, direct friends, mutual friends, and therefore the indirect friends, to deep understand social users rating behaviour diffusions. These factors are amalgamate along to boost the accuracy and relevancy of predictions.


Keywords


Twitter information, naive Bayes Classi

Full Text:

PDF

References


“PersonalizedRecommendation Combining User Interest and Social Circle XuemingQian, Member”, IEEE He Feng, Guoshuai Zhao, Tao Mei, Senior Member, IEEE

“Personalized Recommendation Based on Reviews and Ratings Alleviating the Sparsity Problem of Collaborative Filtering” JingnanXu Department of ComputerScienceZhejiang University Zhejiang,P.R. Chinaxujingnan308@gmail.com XiaolinZhengDepartment of Computer Science Zhejiang UniversityZhejiang, P.R. Chinaxlzheng@zju.edu.cn

“A Matrix Factorization Technique with Trust Propagation for Recommendation in Social Networks” Mohsen JamaliSchool of Computing ScienceSimon Fraser UniversityBurnaby, BC, Canada mohsen_jamali@cs.sfu.caMartin EsterSchool of Computing Science Simon Fraser niversityBurnaby, BC, Canadaester@cs.sfu.ca

“Social Contextual Recommendation” Meng Jiang, Peng Cui, Rui Liu, Qiang Yang, Fei WangWenwu Zhu, Shiqiang YangBeijing Key Laboratory of Networked MultimediaDepartment of Computer Science and Technology, Tsinghua University, Beijing, ChinaHealthcare Transformation Group, IBM T J Watson Research Center, USADepartment of Computer Science and Engineering, Hong Kong University of Science and Technology.

Circle-based Recommendation in Online Social Networks Xiwang Yang ECE DepartmentPolytechnic Institute of NYUBrooklyn, New York

xyang01@students.poly.eduHaraldSteck_Bell LabsAlcatel-LucentMurray Hill, New Jerseyhsteck@gmail.com

Networking and Computing (MobiHoc ’05), 2005.

H. Kanayama and T. Nasukawa, “Fully automatic lexicon expansion for domain-oriented sentiment analysis,” in EMNLP’06, pp. 355-363.

Z. Chen, J. R. Jang, and C. Lee, “A kernel framework for content-based artist recommendation system in music,” IEEE Trans. Multimedia, vol. 13, no. 6, 2011.

K. Lee, and K. Lee, “Using dynamically promoted experts for music recommendation,” IEEE Trans. Multimedia, vol. 16, no. 5, 2014.

Z. Wang, L. Sun, W. Zhu, S. Yang, H. Li, and D. Wu, “Joint social and content recommendation for user-generated videos in online social network,” IEEE Trans. Multimedia, vol. 15, no. 3, 2013.

X. Ding, B. Liu, and P. S. Yu, “A holistic lexicon-based approach to opinion mining,” in WSDM '08, pp. 231-240.

Y. Zhang, G. Lai, M. Zhang, Y. Zhang, Y. Liu, S. Ma, “Explicit factor models for explainable recommendation based on phrase-level sentiment analysis,” in proceedings of the 37th international ACM SIGIR conference on Research &


Refbacks

  • There are currently no refbacks.