News Credibility Analysis on Facebook using User Interaction Data
Interaction-based machine learning for Bengali-language news credibility.
Amid the COVID-19 outbreak, we initially focused on detecting fake health-related news on Bengali-language Facebook content. Recognizing information disparities, we transitioned from a content-based approach to a language-independent, computationally efficient interaction metric based method. The scope was further expanded beyond health related news to general news.
We employed machine learning methodologies to classify public Facebook posts based on authenticity. The proposed method outperformed existing content-based and NLP-based solutions. Furthermore, our research demonstrated that user reactions or interactions with the system vary significantly based on the content of news articles, offering a useful way to gain valuable insights.
- Paper: Interaction Based Credibility Analysis of News on Facebook Using Machine Learning Methodologies (SITIS-2022).
- Tech: scikit-learn, pandas, matplotlib.
- Method: Predictive Modeling Study; Analysis: Exploratory Data Analysis, Machine Learning.
- Current State: Accepted (SITIS-2022).