IDEAS home Printed from https://ideas.repec.org/a/gam/jftint/v14y2022i10p300-d946575.html
   My bibliography  Save this article

Towards Reliable Baselines for Document-Level Sentiment Analysis in the Czech and Slovak Languages

Author

Listed:
  • Ján Mojžiš

    (Institute of Informatics, Slovak Academy of Sciences, 84507 Bratislava, Slovakia)

  • Peter Krammer

    (Institute of Informatics, Slovak Academy of Sciences, 84507 Bratislava, Slovakia)

  • Marcel Kvassay

    (Institute of Informatics, Slovak Academy of Sciences, 84507 Bratislava, Slovakia)

  • Lenka Skovajsová

    (Institute of Informatics, Slovak Academy of Sciences, 84507 Bratislava, Slovakia)

  • Ladislav Hluchý

    (Institute of Informatics, Slovak Academy of Sciences, 84507 Bratislava, Slovakia)

Abstract

This article helps establish reliable baselines for document-level sentiment analysis in highly inflected languages like Czech and Slovak. We revisit an earlier study representing the first comprehensive formulation of such baselines in Czech and show that some of its reported results need to be significantly revised. More specifically, we show that its online product review dataset contained more than 18% of non-trivial duplicates, which incorrectly inflated its macro F1-measure results by more than 19 percentage points. We also establish that part-of-speech-related features have no damaging effect on machine learning algorithms (contrary to the claim made in the study) and rehabilitate the Chi-squared metric for feature selection as being on par with the best performing metrics such as Information Gain. We demonstrate that in feature selection experiments with Information Gain and Chi-squared metrics, the top 10% of ranked unigram and bigram features suffice for the best results regarding online product and movie reviews, while the top 5% of ranked unigram and bigram features are optimal for the Facebook dataset. Finally, we reiterate an important but often ignored warning by George Forman and Martin Scholz that different possible ways of averaging the F1-measure in cross-validation studies of highly unbalanced datasets can lead to results differing by more than 10 percentage points. This can invalidate the comparisons of F1-measure results across different studies if incompatible ways of averaging F1 are used.

Suggested Citation

  • Ján Mojžiš & Peter Krammer & Marcel Kvassay & Lenka Skovajsová & Ladislav Hluchý, 2022. "Towards Reliable Baselines for Document-Level Sentiment Analysis in the Czech and Slovak Languages," Future Internet, MDPI, vol. 14(10), pages 1-23, October.
  • Handle: RePEc:gam:jftint:v:14:y:2022:i:10:p:300-:d:946575
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1999-5903/14/10/300/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/1999-5903/14/10/300/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Bidyut Hazarika & Kuanchin Chen & Muhammad Razi, 2021. "Are numeric ratings true representations of reviews? A study of inconsistency between reviews and ratings," International Journal of Business Information Systems, Inderscience Enterprises Ltd, vol. 38(1), pages 85-106.
    2. Nabila Mohamad Sham & Azlinah Mohamed, 2022. "Climate Change Sentiment Analysis Using Lexicon, Machine Learning and Hybrid Approaches," Sustainability, MDPI, vol. 14(8), pages 1-28, April.
    3. Gonzalo A. Ruz & Pablo A. Henríquez & Aldo Mascareño, 2022. "Bayesian Constitutionalization: Twitter Sentiment Analysis of the Chilean Constitutional Process through Bayesian Network Classifiers," Mathematics, MDPI, vol. 10(2), pages 1-20, January.
    Full references (including those not matched with items on IDEAS)

    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. Wenzhi Cao & Xingen Yang & Yi Yang, 2023. "A Large-Scale Reviews-Driven Multi-Criteria Product Ranking Approach Based on User Credibility and Division Mechanism," Mathematics, MDPI, vol. 11(13), pages 1-19, July.
    2. Henrik Sällberg & Shujun Wang & Emil Numminen, 2023. "The combinatory role of online ratings and reviews in mobile app downloads: an empirical investigation of gaming and productivity apps from their initial app store launch," Journal of Marketing Analytics, Palgrave Macmillan, vol. 11(3), pages 426-442, September.
    3. Eva L. Jenkins & Dickson Lukose & Linda Brennan & Annika Molenaar & Tracy A. McCaffrey, 2023. "Exploring Food Waste Conversations on Social Media: A Sentiment, Emotion, and Topic Analysis of Twitter Data," Sustainability, MDPI, vol. 15(18), pages 1-26, September.

    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:gam:jftint:v:14:y:2022:i:10:p:300-:d:946575. 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: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.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.