Bias-Aware Lexicon-Based Sentiment Analysis

Sentiment analysis of textual content is widely used for auto-matic summarization of opinions and sentiments expressed by people. With the growing popularity of social media and user-generated content, efficient and effective sentiment analysis is critical to businesses and governments. Lexicon-based methods provide efficiency through their manually de-veloped affective word lists and valence values. However, the predictions of such methods can be biased towards positive or negative polarity thus distorting the analysis. In this paper, we propose Bias-Aware Thresholding (BAT), an ap-proach that can be combined with any lexicon-based method to make it bias-aware. BAT is motivated from cost-sensitive learning where the prediction threshold is changed to reduce prediction error bias. We formally define bias in polarity pre-dictions and present a measure for quantifying it. We eval-uate BAT in combination with AFINN and SentiStrength – two popular lexicon-based methods – on seven real-world datasets. The results show that bias reduces smoothly with an increase in the absolute value of the threshold, and accu-racy increases as well in most cases. We demonstrate that the threshold can be learned reliably from a very small num-ber of labeled examples, and supervised classifiers learned on such small datasets produce poorer bias and accuracy per-formances