IDEAS home Printed from https://ideas.repec.org/a/spr/jclass/v36y2019i3d10.1007_s00357-019-9307-0.html
   My bibliography  Save this article

Comparing the Utility of Different Classification Schemes for Emotive Language Analysis

Author

Listed:
  • Lowri Williams

    (Cardiff University)

  • Michael Arribas-Ayllon

    (Cardiff University)

  • Andreas Artemiou

    (Cardiff University)

  • Irena Spasić

    (Cardiff University)

Abstract

In this paper we investigated the utility of different classification schemes for emotive language analysis with the aim of providing experimental justification for the choice of scheme for classifying emotions in free text. We compared six schemes: (1) Ekman's six basic emotions, (2) Plutchik's wheel of emotion, (3) Watson and Tellegen's Circumplex theory of affect, (4) the Emotion Annotation Representation Language (EARL), (5) WordNet–Affect, and (6) free text. To measure their utility, we investigated their ease of use by human annotators as well as the performance of supervised machine learning. We assembled a corpus of 500 emotionally charged text documents. The corpus was annotated manually using an online crowdsourcing platform with five independent annotators per document. Assuming that classification schemes with a better balance between completeness and complexity are easier to interpret and use, we expect such schemes to be associated with higher inter–annotator agreement. We used Krippendorff's alpha coefficient to measure inter–annotator agreement according to which the six classification schemes were ranked as follows: (1) six basic emotions (α = 0.483), (2) wheel of emotion (α = 0.410), (3) Circumplex (α = 0.312), EARL (α = 0.286), (5) free text (α = 0.205), and (6) WordNet–Affect (α = 0.202). However, correspondence analysis of annotations across the schemes highlighted that basic emotions are oversimplified representations of complex phenomena and as such likely to lead to invalid interpretations, which are not necessarily reflected by high inter-annotator agreement. To complement the result of the quantitative analysis, we used semi–structured interviews to gain a qualitative insight into how annotators interacted with and interpreted the chosen schemes. The size of the classification scheme was highlighted as a significant factor affecting annotation. In particular, the scheme of six basic emotions was perceived as having insufficient coverage of the emotion space forcing annotators to often resort to inferior alternatives, e.g. using happiness as a surrogate for love. On the opposite end of the spectrum, large schemes such as WordNet–Affect were linked to choice fatigue, which incurred significant cognitive effort in choosing the best annotation. In the second part of the study, we used the annotated corpus to create six training datasets, one for each scheme. The training data were used in cross–validation experiments to evaluate classification performance in relation to different schemes. According to the F-measure, the classification schemes were ranked as follows: (1) six basic emotions (F = 0.410), (2) Circumplex (F = 0.341), (3) wheel of emotion (F = 0.293), (4) EARL (F = 0.254), (5) free text (F = 0.159) and (6) WordNet–Affect (F = 0.158). Not surprisingly, the smallest scheme was ranked the highest in both criteria. Therefore, out of the six schemes studied here, six basic emotions are best suited for emotive language analysis. However, both quantitative and qualitative analysis highlighted its major shortcoming – oversimplification of positive emotions, which are all conflated into happiness. Further investigation is needed into ways of better balancing positive and negative emotions.

Suggested Citation

  • Lowri Williams & Michael Arribas-Ayllon & Andreas Artemiou & Irena Spasić, 2019. "Comparing the Utility of Different Classification Schemes for Emotive Language Analysis," Journal of Classification, Springer;The Classification Society, vol. 36(3), pages 619-648, October.
  • Handle: RePEc:spr:jclass:v:36:y:2019:i:3:d:10.1007_s00357-019-9307-0
    DOI: 10.1007/s00357-019-9307-0
    as

    Download full text from publisher

    File URL: http://link.springer.com/10.1007/s00357-019-9307-0
    File Function: Abstract
    Download Restriction: Access to the full text of the articles in this series is restricted.

    File URL: https://libkey.io/10.1007/s00357-019-9307-0?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Stefanie Haustein & Timothy D. Bowman & Kim Holmberg & Andrew Tsou & Cassidy R. Sugimoto & Vincent Larivière, 2016. "Tweets as impact indicators: Examining the implications of automated “bot” accounts on Twitter," Journal of the Association for Information Science & Technology, Association for Information Science & Technology, vol. 67(1), pages 232-238, January.
    2. Laros, Fleur J.M. & Steenkamp, Jan-Benedict E.M., 2005. "Emotions in consumer behavior: a hierarchical approach," Journal of Business Research, Elsevier, vol. 58(10), pages 1437-1445, October.
    3. Lawrence Hubert & Phipps Arabie, 1985. "Comparing partitions," Journal of Classification, Springer;The Classification Society, vol. 2(1), pages 193-218, December.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Vuk Batanović & Miloš Cvetanović & Boško Nikolić, 2020. "A versatile framework for resource-limited sentiment articulation, annotation, and analysis of short texts," PLOS ONE, Public Library of Science, vol. 15(11), pages 1-30, November.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Haase, Janina & Wiedmann, Klaus-Peter & Labenz, Franziska, 2022. "Brand hate, rage, anger & co.: Exploring the relevance and characteristics of negative consumer emotions toward brands," Journal of Business Research, Elsevier, vol. 152(C), pages 1-16.
    2. Wu, Han-Ming & Tien, Yin-Jing & Chen, Chun-houh, 2010. "GAP: A graphical environment for matrix visualization and cluster analysis," Computational Statistics & Data Analysis, Elsevier, vol. 54(3), pages 767-778, March.
    3. José E. Chacón, 2021. "Explicit Agreement Extremes for a 2 × 2 Table with Given Marginals," Journal of Classification, Springer;The Classification Society, vol. 38(2), pages 257-263, July.
    4. Garaus, Marion & Wagner, Udo, 2016. "Retail shopper confusion: Conceptualization, scale development, and consequences," Journal of Business Research, Elsevier, vol. 69(9), pages 3459-3467.
    5. Luke Butcher & Ian Phau & Min Teah, 2016. "Brand prominence in luxury consumption: Will emotional value adjudicate our longing for status?," Journal of Brand Management, Palgrave Macmillan, vol. 23(6), pages 701-715, November.
    6. Roberto Rocci & Stefano Antonio Gattone & Roberto Di Mari, 2018. "A data driven equivariant approach to constrained Gaussian mixture modeling," Advances in Data Analysis and Classification, Springer;German Classification Society - Gesellschaft für Klassifikation (GfKl);Japanese Classification Society (JCS);Classification and Data Analysis Group of the Italian Statistical Society (CLADAG);International Federation of Classification Societies (IFCS), vol. 12(2), pages 235-260, June.
    7. Redivo, Edoardo & Nguyen, Hien D. & Gupta, Mayetri, 2020. "Bayesian clustering of skewed and multimodal data using geometric skewed normal distributions," Computational Statistics & Data Analysis, Elsevier, vol. 152(C).
    8. Zhu, Xuwen & Melnykov, Volodymyr, 2018. "Manly transformation in finite mixture modeling," Computational Statistics & Data Analysis, Elsevier, vol. 121(C), pages 190-208.
    9. Amiri, Babak & Karimianghadim, Ramin, 2024. "A novel text clustering model based on topic modelling and social network analysis," Chaos, Solitons & Fractals, Elsevier, vol. 181(C).
    10. Heyes, Anthony & Kapur, Sandeep, 2012. "Angry customers, e-word-of-mouth and incentives for quality provision," Journal of Economic Behavior & Organization, Elsevier, vol. 84(3), pages 813-828.
    11. Li, Pai-Ling & Chiou, Jeng-Min, 2011. "Identifying cluster number for subspace projected functional data clustering," Computational Statistics & Data Analysis, Elsevier, vol. 55(6), pages 2090-2103, June.
    12. A van Giessen & K G M Moons & G A de Wit & W M M Verschuren & J M A Boer & H Koffijberg, 2015. "Tailoring the Implementation of New Biomarkers Based on Their Added Predictive Value in Subgroups of Individuals," PLOS ONE, Public Library of Science, vol. 10(1), pages 1-14, January.
    13. Inés López López & Salvador Ruiz de Maya, 2012. "When hedonic products help regulate my mood," Marketing Letters, Springer, vol. 23(3), pages 701-717, September.
    14. Yaeji Lim & Hee-Seok Oh & Ying Kuen Cheung, 2019. "Multiscale Clustering for Functional Data," Journal of Classification, Springer;The Classification Society, vol. 36(2), pages 368-391, July.
    15. Stefano Tonellato & Andrea Pastore, 2013. "On the comparison of model-based clustering solutions," Working Papers 2013:05, Department of Economics, University of Venice "Ca' Foscari".
    16. Elvira Pelle & Roberta Pappadà, 2021. "A clustering procedure for mixed-type data to explore ego network typologies: an application to elderly people living alone in Italy," Statistical Methods & Applications, Springer;Società Italiana di Statistica, vol. 30(5), pages 1507-1533, December.
    17. Renato Cordeiro Amorim, 2016. "A Survey on Feature Weighting Based K-Means Algorithms," Journal of Classification, Springer;The Classification Society, vol. 33(2), pages 210-242, July.
    18. Tom Wilderjans & Eva Ceulemans & Iven Mechelen, 2008. "The CHIC Model: A Global Model for Coupled Binary Data," Psychometrika, Springer;The Psychometric Society, vol. 73(4), pages 729-751, December.
    19. Dong Liu & Changwei Zhao & Yong He & Lei Liu & Ying Guo & Xinsheng Zhang, 2023. "Simultaneous cluster structure learning and estimation of heterogeneous graphs for matrix‐variate fMRI data," Biometrics, The International Biometric Society, vol. 79(3), pages 2246-2259, September.
    20. Yuchen Liang & Guowei Shi & Runlin Cai & Yuchen Yuan & Ziying Xie & Long Yu & Yingjian Huang & Qian Shi & Lizhe Wang & Jun Li & Zhonghui Tang, 2024. "PROST: quantitative identification of spatially variable genes and domain detection in spatial transcriptomics," Nature Communications, Nature, vol. 15(1), pages 1-17, December.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:spr:jclass:v:36:y:2019:i:3:d:10.1007_s00357-019-9307-0. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.springer.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.