Lexicon-based approach outperforms Supervised Machine Learning approach for Urdu Sentiment Analysis in multiple domains

摘要

Web is facilitating people to express their views and opinions on different topics through reviews and blogs. Effective advantages can be reaped from these reviews and blogs by fusing the sentiment knowledge. In this research, Sentiment Analysis of Urdu blogs from multiple domains is done by using the two widely used approaches i.e. the Lexicon-based approach and the Supervised Machine Learning approach. Three well known classifiers i.e. Support Vector Machine, Decision Tree and K Nearest Neighbor are used in case of Supervised Machine Learning approach whereas a wide coverage Urdu Sentiment Lexicon and an efficient Urdu Sentiment Analyzer are used in Lexicon-based approach. In both the approaches the information are fused from two sources to successfully perform Sentiment Analysis. In case of Lexicon-based approach, the two sources are the wide coverage Urdu Sentiment Lexicon and the efficient Urdu Sentiment Analyzer. In case of Supervised Machine Learning approach, the two sources are the un-annotated data and annotated data along with important attributes. After performing Sentiment Analysis using both the approaches, the results are observed carefully and on the basis of experiments performed in this research, it is concluded that the Lexicon-based approach outperforms Supervised Machine Learning approach not only in terms of Accuracy, Precision, Recall and F-measure but also in terms of economy of time and efforts used.