In this study, we aim to construct an emotion detection system, which is capable of recognizing emotions of customers from product feedback forms for customer service. The proposed system integrated the ontology and the fuzzy inference algorithm for analyzing and recognizing various emotions through verbal/spoken sentences. Companies can evaluate users' degree of satisfaction from emotions and automatically find out opinions of interest, saving unnecessary human resources.
In order to tag emotion labels and compute the relation strength between concepts, we have proposed two algorithms: One is the semantic parser based on natural language processing technique and emotion distance calculation; the other is the concept semantic knowledge database (OMCSNet) combined with fuzzy inference algorithm. Each sentence is then sent into the inference engine for determining its corresponding emotion.
Compared with the other baseline systems, our experimental results showed that the emotion recognition rate was increased by 10% on average. The experiments also demonstrated the efficacy of our proposed approaches.
Bibliographic reference. Fang, Ren-Ying / Chen, Bo-Wei / Wang, Jhing-Fa / Wu, Chung-Hsien (2011): "Emotion detection based on concept inference and spoken sentence analysis for customer service", In INTERSPEECH-2011, 1409-1412.