Identification of Negative Comments on Internet Forums

If we can acquire the reviews and comments from social networks or Internet forums about a certain enterprise's products, services or activities, these reviews and comments can be valuable to the enterprise because it can use the information to improve products and services or fix problems in a timely manner. The traditional sources of collecting clients' opinions include surveys with questionnaires, records from call center, and clients' questions on Web forums. However, the information collected from these sources is of high-cost and not efficient because it is usually done by human. In this research, we use a machine learning technique - the Support Vector Machine (SVM) for sentiment classification. First, we use Web crawlers to obtain the reviews and comments of a specific brand, product or service. After obtaining the text data, we use the sentiment classifier to identify negative comments and then report the results to the enterprise. The information not only makes the enterprise handle the complaints in time, but also improves their products or services. In the experimental results, we can see that the results of identifying negative comments are quite good and this automated approach is promising.

[1]  Bo Pang,et al.  Thumbs up? Sentiment Classification using Machine Learning Techniques , 2002, EMNLP.

[2]  Erik Rolland,et al.  Multi-Class Sentiment Analysis with Clustering and Score Representation , 2013, 2013 IEEE 13th International Conference on Data Mining Workshops.

[3]  Hsin-Hsi Chen,et al.  Emotion Classification Using Web Blog Corpora , 2007, IEEE/WIC/ACM International Conference on Web Intelligence (WI'07).

[4]  Chao-Lin Liu,et al.  Sentiment Classification of Short Chinese Sentences , 2010, International Conference on Computational Linguistics.

[5]  Ming Zhou,et al.  A Joint Segmentation and Classification Framework for Sentiment Analysis , 2014, EMNLP.

[6]  Tanvir Ahmad,et al.  Fuzzy based Sentiment Analysis of Online Product Reviews using Machine Learning Techniques , 2014 .

[7]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[8]  Shady Shehata,et al.  Enhancing Search Engine Quality Using Concept-based Text Retrieval , 2007, IEEE/WIC/ACM International Conference on Web Intelligence (WI'07).

[9]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[10]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[11]  Pavel Berkhin,et al.  A Survey of Clustering Data Mining Techniques , 2006, Grouping Multidimensional Data.

[12]  Ming Liu,et al.  Research on Feature Extraction from Chinese Text for Opinion Mining , 2009, 2009 International Conference on Asian Language Processing.

[13]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.