Sentiment Analysis for Konkani Language: Konkani Poetry, a Case Study

Abstract

Sentiment analysis is a part of NLP research. In the present work, we increased the existing corpus of Konkani senti-words by adding 75% more words and employed the Naïve Bayes classifier for the automatic senti-tagging of Konkani poems. We obtained 82% accuracy over a set of 50 poems that have been written by 22 contemporary poets, for which all the words were ensured to be the part of our corpus. We got 70% accuracy for tagging of a set of 10 randomly selected poems. The results are comparable with those of research on automatic classification of Telugu songs (Harika et al. in Proceedings of the 4th workshop on sentiment analysis where AI meets psychology, IJCAI, pp 48-52, 2016, [15]). The performance of the model could rank it third in the list of similar works reported in the literature.

An Ensemble Based Approach for Sentiment Classification in Asian Regional Language

“…The authors employed machine learning techniques such as Naive Bayes, Decision Tree, and Support Vector Machine (SMO) using the Weka tool to reach accuracy of 50.95%, 54.48%, and 51.07% for the electronics product review dataset in Hindi [25]. In the case of Konkani, the authors used a dataset of Konkani poetry with Naive Bayes classification and attained an accuracy of 82.67% [26][27][28]. Furthermore, we have obtained better classification results for ensembled based classifier as 96.77%, 97.77%, for 5-fold and 10-fold cv respectively.…”

“…Logistic regression estimates probabilities using a logistic function, which is the cumulative logistic distribution, to assess the association between a categorical dependent variable and one or more independent variables [24][25][26][27][28]. Logistic regression is a linear approach; however, the logistic function is used to modify the predictions.…”