Ex-Twit: Explainable Twitter Mining on Health Data
This work addresses the need for explainable AI in Twitter mining applications, particularly for health data, but it appears incremental as it combines existing techniques without introducing a fundamentally new approach.
The authors tackled the problem of opaque predictions in machine learning models for Twitter mining by proposing Ex-Twit, a method combining Topic Modeling and LIME to predict topics and explain predictions, demonstrating its effectiveness on health-related Twitter data.
Since most machine learning models provide no explanations for the predictions, their predictions are obscure for the human. The ability to explain a model's prediction has become a necessity in many applications including Twitter mining. In this work, we propose a method called Explainable Twitter Mining (Ex-Twit) combining Topic Modeling and Local Interpretable Model-agnostic Explanation (LIME) to predict the topic and explain the model predictions. We demonstrate the effectiveness of Ex-Twit on Twitter health-related data.