Skip to main content

Semiotic Function of Empathy in Text Emotion Assessment

Abstract

The focus of this paper is to discuss the semiotic aspects of our findings from a project we conducted in the frame of Emotional Text Analysis paradigm. In the project, we intended to create a computer text classifier capable of effectively classifying texts into emotional categories. We agreed that we would need discrete data samples to input into it. For this, we asked 178 informants to give a verdict on the dominant emotion of 48 sample texts. Prior to their assessment of the texts, the informants responded to a questionnaire used to estimate their empathic tendency. A detailed analysis of the informants’ assessments and personal empathetic tendency scores showed a positive correlation. Subsequently, our interest was piqued by the issue of how emotions could be triggered by conventional signs (words). Our findings seem to suggest that words are only used as an expression form insofar as they embody another type of semiotic complexity, thus diverging from the traditional Pearcian triad. In order to develop on these findings, it is therefore the main objective of this paper to provide a biosemiotic model of representation/interpretation of emotions, with particular attention paid to the eliciting of emotions as sign types. In this endeavour, we draw upon K. Kull’s concept of emonic semiotic model realization. Our suggestion is that, when one processes a text that elicits an emotional response, two semiotic facets are relevant: indexicality and emonicity. We argue that it is a main empathetic function to enforce the emonic model of semiosis over the indexical in situations where the interpreter has a choice between the two. As such, the hypothesis of the study is that emotions facilitate a particular type of semiotic mechanism, relying on the mimesis principle.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Data Availability

The data that support the findings of this study are openly available in Git Hub at https://github.com/AlexDel/levheimcube.

Code Availability

The code that supports the findings of this study is openly available https://colab.research.google.com/drive/15_0q1ff7_2fuldHoC1qzh4U7av16qM1V#scrollTo=hWZuCNQIynAI.

References

Download references

Acknowledgements

We want to thank the Russian Foundation for Basic Research for supporting our research (project № 19-012-00205 “Design of Sentiment Classifier for Internet Texts in Russian backed by Lövheim’s Cube Emotion Model”). An early version of this paper was presented at the conference “19th Annual Gathering in Biosemiotics” (Moscow State University, July 1–5th 2019). We are thankful for the feedback we received at the conference.

Funding

The research leading to these results received funding from the Russian Foundation for Basic Research, Grant № 19-012-00205 “Design of Sentiment Classifier for Internet Texts in Russian backed by Lövheim’s Cube Emotion Model”.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Anastasia Kolmogorova.

Ethics declarations

Conflicts of Interest/Competing Interests

The authors have no conflicts of interest to declare that are relevant to the content of this article.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Kolmogorova, A., Kalinin, A. & Malikova, A. Semiotic Function of Empathy in Text Emotion Assessment. Biosemiotics 14, 329–344 (2021). https://doi.org/10.1007/s12304-021-09434-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12304-021-09434-y

Keywords

  • Emotion assessment magnitude
  • Empathy
  • Mirror neurons
  • Sentiment analysis
  • Sign typology
  • Umwelt