Using discussion logic in analyzing online group discussions: A text mining approach

Abstract

Abstract We propose a Discussion Logic-based Text Analytics (DiLTA) framework, which combines theories developed in social science and text mining fields. The framework extracts features that uncover discussion logic and uses these features in analyzing online discussions. A series of models are proposed including conversation disentanglement, coherence analysis, and visualization. Validation experiments showed that DiLTA achieved significantly superior performance over existing text analytics methods in reconstructing internal structure. A case study using DiLTA-enabled visualization on a healthcare forum illustrates the great potential of DiLTA in assisting comprehension of the internal linkage, structure, and logic of online group discussions.