Sentiment and Emotions in Taylor Swift’s Albums. A Journey through the Eras
DOI:
https://doi.org/10.1285/i22390359v71p113Parole chiave:
Taylor Swift, song lyrics, sentiment analysis, emotion detection, large language models.Abstract
American singer-songwriter Taylor Swift has navigated different musical styles throughout her career, ranging from country, to pop, to indie folk. Her albums are characterized by establishing the beginning of new eras, each marked by a defined aesthetics and sound. This research aims to scrutinize the evolution of Taylor Swift’s lyrics throughout her discography in terms of sentiment and emotions. The main objective is to find out whether actual alignment exists between Taylor Swift’s lyrics and the supposed eras that according to the artist have marked her work. To do so, we examine her discography in terms of sentiment and emotions. We use a mixed-methods approach to analyze each album’s lyrics using several advanced text processing tools. To deal with sentiment, we analyze Swift’s discography using an advanced sentiment analysis system that offers time series analysis. On the other hand, we extract the most salient emotions using an advanced corpus query tool designed for content and discourse analysis that allows the identification and raking of emotions according to Parrott’s list. The results show that love and sadness dominate Swift’s discography, with a predominantly negative sentiment. Additionally, there is a mismatch between the emotions in her lyrics and their sentiment classification, indicating that Swift’s style does not rely on explicit positive or negative terms. Instead, her use of rhetorical devices and subtle language conveys meaning through more implicit forms.Riferimenti bibliografici
Abdullah M., Waheed S., and Hossain S. 2023, Sentiment Analysis of Restaurant Reviews Using Machine Learning, in Kaiser M. S., Waheed S., Bandyopadhyay A., Mahmud M., & Ray K. (eds.), Proceedings of the Fourth International Conference on Trends in Computational and Cognitive Engineering (Vol. 618), Springer Nature Singapore, pp. 419-428. https://doi.org/10.1007/978-981-19-9483-8_35
Ameur A., Hamdi S., and Ben Yahia S. 2024, Sentiment Analysis for Hotel Reviews: A Systematic Literature Review, in “ACM Computing Surveys” 56 [2], pp. 1-38. https://doi.org/10.1145/3605152
Aue A. and Gamon M. 2005, Customizing Sentiment Classifiers to New Domains: A Case Study in Proceedings of Recent Advances in Natural Language Processing (RANLP). Recent Advances in Natural Language Processing (RANLP), Borovets, Bulgaria.
Benamara F., Taboada M., and Mathieu Y. 2017, Evaluative language beyond bags of words: Linguistic insights and computational applications in “Computational Linguistics” 43 [1], pp. 201-264. https://doi.org/10.1162/COLI_a_00278
Chatterjee A., Narahari K. N., Joshi M., and Agrawal P. 2019, SemEval-2019 Task 3: EmoContext Contextual Emotion Detection in Text, in May J., Shutova E., Herbelot A, Zhu X., Apidianaki M., & Mohammad S. M. (eds.), Proceedings of the 13th International Workshop on Semantic Evaluation, Association for Computational Linguistics, pp. 39-48. https://doi.org/10.18653/v1/S19-2005
Choi J., Song J.-H., and Kim Y. 2018, An Analysis of Music Lyrics by Measuring the Distance of Emotion and Sentiment, in 2018 19th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD), pp. 176-181. https://doi.org/10.1109/SNPD.2018.8441085
De Clercq O., Lefever E., Jacobs G., Carpels T., and Hoste V. 2017, Towards an integrated pipeline for aspect-based sentiment analysis in various domains in Balahur A., Mohammad S. M., van der Goot E. (eds.), Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pp. 136-142. https://doi.org/10.18653/v1/W17-5218
Douglas-Cowie E., Cox C., Martin J.-C., Devillers L., Cowie R., Sneddon I., McRorie M., Pelachaud C., Peters C., Lowry O., Batliner A., and Hönig F. 2011, The HUMAINE Database in Cowie R., Pelachaud C., & Petta P. (eds.), Emotion-Oriented Systems, Springer Berlin Heidelberg, pp. 243-284. https://doi.org/10.1007/978-3-642-15184-2_14
Du J. 2024, Sentiment Analysis and Lyrics Theme Recognition of Music Lyrics Based on Natural Language Processing, in “Journal of Electrical Systems” 20[9s], pp. 315-321.
Ekman P. 1992, An argument for basic emotions, in “Cognition and Emotion” 6[3-4], pp. 169-200. https://doi.org/10.1080/02699939208411068
Green C. 2024. Your Expert Guide To Taylor Swift’s Eras (And What Defined Each One), in “Marie Claire”. https://www.marieclaire.com.au/life/taylor-swift-eras-explained/ (13.02.2025)
Jagwani A. 2021, “Red (Taylor’s Version)” is a mosaic of nostalgia and heartbreak, in The Brown Daily Herald. https://www.browndailyherald.com/article/2021/11/red-taylors-version-is-a-mosaic-of-nostalgia-and-heartbreak (15.08.2024)
Khan A., Baharudin B., and Khan K. 2010, Sentence based sentiment classification from online customer reviews, in FIT ’10: Proceedings of the 8th International Conference on Frontiers of Information Technology, Association for Computing Machinery, New York, pp. 1-6 https://doi.org/10.1145/1943628.1943653
Kumar S., Akhtar Md. S., Cambria E., and Chakraborty T. 2024, SemEval 2024—Task 10: Emotion Discovery and Reasoning its Flip in Conversation (EDiReF), in Ojha A. Kr., Doğruöz A. S., Tayyar Madabushi H., Da San Martino G., Rosenthal S., & Rosá A. (eds.), Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), Association for Computational Linguistics, (pp. 1933-1946). https://doi.org/10.18653/v1/2024.semeval-1.270
Lei L., and Liu D. 2021, Conducting Sentiment Analysis. Cambridge University Press, Cambridge.
Liu B. 2015, Sentiment Analysis: Mining opinions, sentiments, and emotions. Cambridge University Press, Cambridge. https://doi.org/10.1017/CBO9781139084789
Moreno-Ortiz A. 2019, Mi opinión cuenta: La expresión del sentimiento en la red, in Robles Avila A. & Moreno-Ortiz A. (eds.), Comunicación mediada por ordenador: La lengua, el discurso y la imagen, Cátedra, pp. 38-74.
Moreno-Ortiz A. 2023, Lingmotif 2 (Versión 2.0) [Python 3]. Universidad de Málaga. http://www.lingmotif.com
Moreno-Ortiz A. 2024ª, Corpus Sense (Versión 0.9.2) [Python 3]. Universidad de Málaga. https://corpus-sense.app
Moreno-Ortiz A. 2024b, Making Sense of Large Social Media Corpora: Keywords, Topics, Sentiment, and Hashtags in the Coronavirus Twitter Corpus. Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-52719-7
Moreno-Ortiz A., and Pérez-Hernández C. 2018, Lingmotif-lex: A Wide-coverage, State-of-the-art Lexicon for Sentiment Analysis, in Calzolari N., Choukri K., Cieri C., Declerck T., Goggi S., Hasida K., Isahara H., Maegaard B., Mariani J., Mazo H., Moreno A., Odijk J., Piperidis S., Tokunaga T. (eds), Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), pp. 2653-2659.
Moreno-Ortiz A., Salles-Bernal S., and Orrequia-Barea A. 2019, Design and validation of annotation schemas for aspect-based sentiment analysis in the tourism sector, in “Information Technology & Tourism” 21[4], pp. 535-557. https://doi.org/10.1007/s40558-019-00155-0
Muhammad A., Wiratunga N., and Lothian R. 2016, Contextual sentiment analysis for social media genres, in “Knowledge-Based Systems” 108, pp. 92-101.
Mylrea H. (2020). Taylor Swift – ‘Evermore’ review: The freewheeling younger sibling to ‘Folklore’, in “NME”. https://www.nme.com/reviews/taylor-swift-evermore-review-2835933 (13.02.2025)
Nandwani P., and Verma R. 2021, A review on sentiment analysis and emotion detection from text, in “Social Network Analysis and Mining” 11[1], p. 81. https://doi.org/10.1007/s13278-021-00776-6
Nanji N. 2024, Taylor Swift: The Tortured Poets Department broke Spotify record, in “BBC”. https://www.bbc.com/news/entertainment-arts-68863614 (20.04.2024)
Parrott W. G. (ed.) 2001, Emotions in Social Psychology: Key Readings in Social Psychology. Psychology Press.
Penn D., and Trust G. (2024). Taylor Swift’s Songwriting and Production Analyzed: 13 Secrets to Her Chart Success, in “Billboard”. https://www.billboard.com/lists/taylor-swift-songwriting-production-analyzed/. (13.02.2025)
Petridis A. (2024). Taylor Swift: 1989 review – leagues ahead of the teen-pop competition, in “The Guardian”. https://www.theguardian.com/music/2014/oct/24/taylor-swift-1989-review (13.02.2025)
Qwen Team 2024, Qwen2.5: A Party of Foundation Models [Shell]. Qwen. https://github.com/QwenLM/Qwen2.5
Sharma V., Agarwal A., Dhir R., and Sikka G. 2016, Sentiments mining and classification of music lyrics using SentiWordNet, in 2016 Symposium on Colossal Data Analysis and Networking (CDAN), pp. 1-6. https://doi.org/10.1109/CDAN.2016.7570965
Singh V. K., Piryani R., Uddin A., and Waila P. 2013, Sentiment analysis of movie reviews and blog posts, in Kalra B. M., Garg D., Prasad R., Kumar S. (eds.), 2013 3rd IEEE International Advance Computing Conference (IACC), pp. 893-898. https://doi.org/10.1109/IAdCC.2013.6514345
Taboada M. 2016, Sentiment Analysis: An Overview from Linguistics, in “Annual Review of Linguistics” 2 [2], pp. 325-347. https://doi.org/10.1146/annurev-linguistics-011415-040518
##submission.downloads##
Pubblicato
Fascicolo
Sezione
Licenza
Authors who publish with this publication accept all the terms and conditions of the Creative Commons license at the link below.
Gli autori che pubblicano in questa rivista accettano i termini e le condizioni specificate nella licenza Creative Commons di cui al link sottostante.
http://creativecommons.org/licenses/by-nc-nd/3.0/it/legalcode
