AUTHOR=Niu Shulin TITLE=Emotion research on education public opinion based on text analysis and deep learning JOURNAL=Frontiers in Psychology VOLUME=13 YEAR=2022 URL=https://www.frontiersin.org/journals/psychology/articles/10.3389/fpsyg.2022.992419 DOI=10.3389/fpsyg.2022.992419 ISSN=1664-1078 ABSTRACT=

Education public opinion information management is an important research focus in the field of Education Data Mining (EDM). In this paper, we classify the education data information based on the traditional Flat-OCC model. From the cognitive psychology perspective, we identify up to 12 kinds of emotions, including sadness and happiness. In addition, the EMO-CBOW model is also proposed in this paper to further identify emotion by using various emoticons in educational data sets. The empirical result shows that (1) the proposed Flat-OCC model can classify and identify the emotion of education public opinion data well; and (2) for the recognition of educational emotion classification, the categorization accuracy of the Flat-OCC+EMO-CBOW model is significantly higher than that of a single Flat-OCC model, which reveals that the emotional-pack-based model we propose can enhance our benchmark model.