Abstract
Nowadays sentiment and emotion analyses are widespread methodologies. However, most of all related tasks in classification manner use discrete classes as target variables: Positive vs Negative (sometimes accompanied by Neutral class), or discrete emotion classes (as Anger, Joy, Fear, etc.). Nonetheless, it is more likely that emotion is not discrete. In this paper, we argue that regression is more natural way to evaluate and predict emotions in text and apply regression framework in study of using Lövheim Cube emotional model for emotion analysis. A regression approach for predicting a point in 3-d space or a configuration of its diagonals can provide us with detailed analytics from an emotional diversity perspective. The preliminary results on regression values prediction performed by five different models demonstrate the need of optimization in regard to a precision. The additional conclusion is that the accuracy of classification is not affected significantly by the target variable type.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Mum has got it into her head that I’m an anorexic, since she has been seeing a lot of TV shows about it. Now she makes a scene forcing me to eat huge portions, doesn’t let me out of the kitchen till I finish eating, once she even raised her hand on me! And who needs to be treated after that… I'm just thin, fast metabolism + I don't lead a sedentary life. And my dad has always been thin, although he has eaten a lot and often. But no, Malakhov, Malysheva and some other guy from TV know better. Shame _ Excitement. Disgust _ Anger. Fear _ Surprise. Enjoyment _ Distress\Anguish.
References
Calvo, R.A., Kim, S.M.: Emotions in text: dimensional and categorical models. Comput. Intell. 29(3), 527–543 (2013). https://doi.org/10.1111/j.1467-8640.2012.00456.x
Ekman, P.: An argument for basic emotions. Cogn. Emot. 6(3–4), 169–200 (1992). https://doi.org/10.1080/02699939208411068
Tomkins, S.S.: Affect Imagery Consciousness. The Positive Affects, vol. 1. Springer, New York (1962)
Plutchik, R.: Emotions: a general psychoevolutionary theory. In: Scherer, K., Ekman, P. (eds.) Approaches to emotion, pp. 197–219. Lawrence Erlbaum Associates, Hillsdale (1984). https://doi.org/10.4324/9781315798806
Bhowmick, P.K., Basu, A., Mitra, P.: Reader perspective emotion analysis in text through ensemble based multi-label classification framework. Comput. Inf. Sci. 2(4), 64–74 (2009). https://doi.org/10.5539/cis.v2n4p64
Alm, C.O., Rot, D., Sproat, R.: Emotions from text: Machine learning for text-based emotion prediction. In: Raymond, J. (ed.) Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, pp. 579–586. Association for Computational Linguistics, Vancouver (2005)
Volkova, E., Mehler, B., Meurers, W.D., Gerdemann, D., Bülthoff, H.: Emotional perception of fairy tales: achieving agreement in emotion annotation of text. In: Inkpen, D., Strapparava, C. (eds.) Proceedings of the NAACL HLT 2010 Workshop on Computational Approaches to Analysis and Generation of Emotion in Text, pp. 98–106. Association for Computational Linguistics, Los Angeles (2010)
Barrett, L.F.: Are emotions natural kinds? Perspect. Psychol. Sci. 1(1), 28–58 (2006). https://doi.org/10.1111/j.1745-6916.2006.00003.x
Russell, J.A.: A circumplex model of affect. J. Pers. Soc. Psychol. 39(6), 1161–1178 (1980). https://doi.org/10.1037/h0077714
Osgood, C.E., May, W.H., Miron, M.S.: Cross-Cultural Universals of Affective Meaning. University of Illinois Press, Urbana (1975)
Lövheim, H.: A new three-dimensional model for emotions and monoamine neurotransmitters. Med. Hypotheses 78, 341–348 (2012). https://doi.org/10.1016/j.mehy.2011.11.016
Gunes, H., Pantic, M.: Automatic, dimensional and continuous emotion recognition. International Journal of Synthetic Emotions 1(1), 68–99 (2010). https://doi.org/10.4018/jse.2010101605
Önal, I., Ertuğrul, A.M.: Effect of using regression in sentiment analysis. In: 22nd Signal Processing and Communications Applications Conference (SIU), pp. 1822–1825. IEEE, Trabzon (2014). https://doi.org/10.1109/SIU.2014.6830606
Tian, L., Lai, C., Moore, J.D.: Polarity and intensity: the two aspects of sentiment analysis. In: Zadeh, A., Liang, P.P., Morency, L.-Ph., Poria, S., Cambria, E., Scherer, S. (eds.) Proceedings of Grand Challenge and Workshop on Human Multimodal Language (Challenge-HML), pp. 40–47. Association for Computational Linguistics, Melbourne (2018). https://doi.org/10.18653/v1/W18-3306
Alotaibi, F.M.: Classifying text-based emotions using logistic regression. VAWKUM Trans. Comput. Sci. 7(1), 31–37 (2019). https://doi.org/10.21015/vtcs.v16i2.551
Mashal, S.X., Asnani, K.: Emotion intensity detection for social media data. In: Proceedings of the 2017 International Conference on Computing Methodologies and Communication (ICCMC), pp. 155–158. IEEE, Erode (2017). https://doi.org/10.1109/ICCMC.2017.8282664
Akhtar, M.S., Ekbal, A., Cambria, E.: How intense are you? Predicting intensities of emotions and sentiments using stacked ensemble. IEEE Comput. Intell. Mag. 15(1), 64–75 (2020). https://doi.org/10.1109/MCI.2019.2954667
Kolmogorova, A., Kalinin, A., Malikova, A.: Non-discrete sentiment dataset annotation: case study for Lövheim Cube emotional model. In: Alexandrov, D.A., et al. (eds.) DTGS 2020. CCIS, vol. 1242, pp. 154–164. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-65218-0_12
Kalinin, A., Kolmogorova, A., Malikova, A.: Non-discrete sentiment annotation for Lövheim Cube. Google Colab Notebook (2021). https://colab.research.google.com/drive/15_0q1ff7_2fuldHoC1qzh4U7av16qM1V
Acknowledgements
The research is supported by the Russian Foundation for Basic Research, project No. 19–012-00205 “Design of sentiment classifier for Internet-texts in Russian backed by Lövheim's Cube emotional model”.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Kolmogorova, A., Kalinin, A., Malikova, A. (2022). Lövheim Cube-Backed Emotion Analysis: From Classification to Regression. In: Alexandrov, D.A., et al. Digital Transformation and Global Society. DTGS 2021. Communications in Computer and Information Science, vol 1503. Springer, Cham. https://doi.org/10.1007/978-3-030-93715-7_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-93715-7_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-93714-0
Online ISBN: 978-3-030-93715-7
eBook Packages: Computer ScienceComputer Science (R0)