“Something Something Hota Hai!” An Explainable Approach towards Sentiment Analysis on Indian Code-Mixed Data

Abstract

The increasing use of social media sites in countries like India has given rise to large volumes of code-mixed data. Sentiment analysis of this data can provide integral insights into people's perspectives and opinions. Codemixed data is often noisy in nature due to multiple spellings for the same word, lack of definite order of words in a sentence, and random abbreviations. Thus, working with codemixed data is more challenging than monolingual data. Interpreting a model's predictions allows us to determine the robustness of the model against different forms of noise. In this paper, we propose a methodology to integrate explainable approaches into code-mixed sentiment analysis. By interpreting the predictions of sentiment analysis models we evaluate how well the model is able to adapt to the implicit noises present in code-mixed data.