A virtual community question and answer suitability determination model

In this information-explosion era, the quality of collective intelligence is not easy to control. Knowledge demanders are required to invest an amount of time in evaluating the collective intelligence quality of virtual community to acquire correct knowledge. In addition, some knowledge providers might provide poor quality information in this circumstance and overall collective intelligence quality would be affected. The knowledge providers would reduce the willingness to share knowledge. Therefore, this paper develops a virtual community question and answer suitability determination (QASD) model to enhance collective intelligence quality. This proposed model analyzes the Q&A title, Q&A content, and the discussion and employs keyword extraction, article’s core information extraction, article similarity determination and semantic analysis techniques to determine the quality of Q&A, the suitability of Q&A content, and the suitability of Q&A semantics. After that, the integrated suitability score between target question and answer can be obtained and regarded as the reference for knowledge demanders in acquiring correct knowledge in virtual community. In order to demonstrate applicability of the proposed methodology, a web-based system is also established based on the proposed model. Furthermore, a real-world case is applied to evaluate the proposed model. The verification results show that when the system maintains about 600 training data, the indicator performance can be improved to 80% (Recall Rate) and 85% (Accuracy Rate), and the system performance continues to grow with increasing training amount and reaches the stable and better performance level. Hence, the developed system is a high-performance Q&A suitability determination system. As a whole, this paper provides an approach for virtual community to efficiently evaluate the suitability of Q&A.