A programme for recognizing the emotional colouring of texts was developed by scientists from the Siberian Federal University, RIA Novosti reports. According to the authors of the study, their development can not only flexibly assess the nature of certain materials but also generate texts with the right mood for education. The results are published in the Biosemiotics journal.
In the course of a series of experiments, the specialists analyzed how individual words and whole texts “trigger” certain experiences in a reader and on the basis of the data obtained, they developed a flexible computer system for classifying texts by the nature of emotional colouring.
“Our system allows not only to determine the emotional colouring of a text by a variety of signs but also helps to generate materials with a given mood. We have already managed to apply it to teaching the Russian language to foreign students: it turned out that joyful texts give a noticeably less educational effect than sad ones,” the head of the study, the Head of the Department of Romance Languages and Applied Linguistics of the Siberian Federal University, Anastasia Kolmogorova, said.
For the experiment, the scientists used 15 thousand posts from 3 groups of the VK network distributed over 8 emotions. During the study, two thousand participants were presented with four thousand randomly selected texts for evaluation using a special interface. In addition, the specialists asked 178 informants to fill out a questionnaire that was used to determine the tendency to empathy.
The researchers explained that they were interested in how empathy can influence the interpretation of words as triggers of emotions. According to the scientists, if a person has a low level of empathy, in the phrase “the girl cried” he concentrates on the word “cry”, which simply denotes the emotion of the girl. A person with a high level of empathy interprets the phrase as an “emon”, that is, he experiences the same state as the girl.
Currently, the university specialists finish the development of the system, which they intend to implement as a multifunctional commercial application. Also, the research team plans to study the influence of such factors as age, gender, and profession on the perception of the emotionality of a text.