A web-based system for emotion vector extraction

The ability of assessing the affective information content is ofincreasing interest in applications of computer science, e.g. in human machineinterfaces, recommender systems, social robots. In this project, the architectureof a semantic system of emotions is designed and implemented, to quantify theemotional content of short sentences by evaluating and aggregating the semanticproximity of each term in the sentence from the basic emotions defined in apsychological model of emotions (e.g. Ekman, Plutchick, Lovheim). Our modelis parametric with respect to the semantic proximity measures, focusing onweb-based proximity measures, where data needed to evaluate the proximity canbe retrieved from search engines on the Web. To test the performances of themodel, a software system has been developed to both collect the statistical dataand perform the emotion analysis. The system automatizes the phases of sentencepreprocessing, search engine query, results parsing, semantic proximitycalculation and the final phase of ranking of emotions.