EMOJIS AS PREDICTORS IN LOVHEIM CUBE BACKED MULTI-CLASS SENTIMENT ANALYSIS: CAN WE REALLY TRUST THEM?
(STEF92 Technology, 2019, A. Kolmogorova, A. Kalinin, A. Malikova)
Show more
When dealing with multiclass classification problem one has to search for reliable and robust predictors to increase the quality of performance that decreases drastically with growth of classes number. In our research, we propose the sentiment analysis method backed by Lovheim Cube Emotional model including 8 emotional classes unlike traditional two (negative/ positive). To increase the accuracy in case of multi-class classification we need to extract more features from the text than it is usually demanded for bin...

