On the Effect of Emotion Identification from Limited Translated Text Samples Using Computational Intelligence

Abstract Emotion identification from text data has recently gained focus of the research community. This multiple utilities in an assortment domains. Many times, original is written a different language and end-user translates it to her native using online utilities. Therefore, this paper presents framework detect emotions on translated four languages. The source English, whereas target languages include Chinese, French, German, Spanish. Computational intelligence (CI) techniques are applied extract features, dimensionality reduction, classification into five basic classes emotions. Results show that when English accuracy higher than others, i.e., 99.04%. Whereas, same Chinese language, its detection rate lowest among It concluded remain preserved after translation some extent. Framework consists TFIDF features. PCA Discriminant Analysis perform good data.