An adaptive neuro-fuzzy inference system (ANFIS) for sentiment analysis classification
Amit Kumar Srivastava, Pooja Pooja, Tanveer Jahan Siddiqui · 2025
Currently, due to the increasing popularity of online applications with platforms for sharing opinions about services and products through social media, fuzzy logic approaches are increasingly used in sentiment analysis research. In this paper, we propose an adaptive neuro-fuzzy inference system “ANFIS” for the classification of Sentiment analysis based on fuzzy logic. To improve the prediction accuracy as much as possible, the paper compares the Fuzzy Inference System (FIS) model with the adaptive neuro-fuzzy inference system (ANFIS) model. The polarity and subjectivity from Textblob are used by the ANFIS for input. The ANFIS outperforms the Mamdani fuzzy inference system (FIS) as evidenced by the lower RMSE.