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. Developing robust explainability techniques which explain why models make their predictions becomes essential. In this paper, we propose an adequate methodology to integrate explainable approaches into code-mixed sentiment analysis.
翻译:印度等国家越来越多地使用社交媒体网站,由此产生了大量代码混合数据。对这些数据的敏感性分析可以使人们对观点和观点有整体的洞察力。开发强有力的解释技术,解释为什么模型的预测变得至关重要。在本文中,我们提出了将可解释的方法纳入代码混合情绪分析的适当方法。