Analysis of Spotify Spanish spoken profiles in Twitter

Boté-Vericad, Juan-José Analysis of Spotify Spanish spoken profiles in Twitter., 2022 . In BOBCATSSS Conference, Debrecen (Hungary), May 2022. [Conference paper]

[thumbnail of Analysis of Spotify Spanish spoken profiles in Twitter.pdf]
Preview
 Text
Analysis of Spotify Spanish spoken profiles in Twitter.pdf - Published version
Available under License Creative Commons Attribution.
Download (467kB) | Preview

English abstract

Twitter is a social networking site where brands create profiles and interact with their audience. Brands also look for new audiences to consume their products or services. In some cases, they create different profiles for different countries or linguistics regions. The written language is the major Twitter expression. Multimedia elements such as images or videos help to spread the message and the interaction with the audience. In this study, we analyze the different profiles of Spotify in the Spanish language addressed to different spoken Spanish countries. Spotify has different profiles on Twitter addressing the content to different spoken Spanish language countries. These profiles are addressed to Spain and South American countries such as Argentina, Chile, Colombia, Mexico. Finally, there is a profile under the name LATAM who is addressed to the rest of the Spanish spoken countries in South America. All these profiles have different audiences, having also differences in the number of followers. In all these countries, Spanish is spoken with different linguistic variations. As a result, the message is different. Consequently, audience interaction and engagement may vary from one profile to another depending on the written language used. The analysis considers these Spanish linguistic variations. We perform a sentimental analysis of these Spanish-spoken profiles, looking for differences in Spanish variations. We also combine the analysis with topic modeling and the uses of hashtags. Spanish linguistic variations may influence the analysis but in the engagement of the profile itself too. Our results show that while messages are similar in the way they are written, engagement with the audience varies from profile to profile. We conclude that Spanish variations influence engagement and commercial companies should consider a similar strategy. We suggest not unifying under a unique spoken Spanish version for the promotion of products and services in Spanish spoken countries.

Item type: Conference paper
Keywords: Twitter; Spotify; Data mining; Spanish variations; Sentiment Analysis; R libraries
Subjects: B. Information use and sociology of information
C. Users, literacy and reading.
D. Libraries as physical collections.
E. Publishing and legal issues.
I. Information treatment for information services
I. Information treatment for information services > IE. Data and metadata structures.
I. Information treatment for information services > IM. Open data
J. Technical services in libraries, archives, museum.
L. Information technology and library technology
Depositing user: Juan-José Boté-Vericad
Date deposited: 22 Apr 2024 07:14
Last modified: 22 Apr 2024 07:14
URI: http://hdl.handle.net/10760/45713

References

Csardi, G., Wormer, T., Ceglowski, M., Rideout, J. R., & Johnson, and K. S. (2021). Franc: Detect the language of text (1.1.4) [Computer software]. https://CRAN.R-project.org/package=franc

Dijkstra, J., Heeringa, W., Jongbloed-Faber, L., & Van de Velde, H. (2021). Using Twitter Data for the Study of Language Change in Low-Resource Languages. A Panel Study of Relative Pronouns in Frisian. Frontiers in Artificial Intelligence, 4. https://www.frontiersin.org/article/10.3389/frai.2021.644554

Donoso, G., & Sánchez, D. (2017). Dialectometric analysis of language variation in Twitter. Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial), 16-25. https://doi.org/10.18653/v1/W17-1202

Gonçalves, B., & Sánchez, D. (2014). Crowdsourcing Dialect Characterization through Twitter. PLOS ONE, 9(11), e112074. https://doi.org/10.1371/journal.pone.0112074

Hornik, K., Mair, P., Rauch, J., Geiger, W., Buchta, C., & Feinerer, I. (2013). The textcat package for ngram based text categorization in r. Journal of Statistical Software, 52, 1–17. https://doi.org/10.18637/jss.v052.i06

Huang, Y., Guo, D., Kasakoff, A., & Grieve, J. (2016). Understanding U.S. regional linguistic variation with Twitter data analysis. Computers, Environment and Urban Systems, 59, 244-255. https://doi.org/10.1016/j.compenvurbsys.2015.12.003

Miletic, F., Przewozny-Desriaux, A., & Tanguy, L. (2020). Collecting Tweets to Investigate Regional Variation in Canadian English. Proceedings of the 12th Language Resources and Evaluation Conference, 6255-6264. https://aclanthology.org/2020.lrec-1.767

Mohammad, S., & Turney, P. (2020). NRC Emotion Lexicon. http://saifmohammad.com/WebPages/NRC-Emotion-Lexicon.htm

Mouselimis, L. (2022). Efficient Learning of Word Representations and Sentence Classification. https://cran.r-project.org/web/packages/fastText/index.html

Omar, A., Ethleb, H., & Hashem, M. E. (2020). Mapping Linguistic Variations in Colloquial Arabic through Twitter: A Centroid-based Lexical Clustering Approach. International Journal of Advanced Computer Science and Applications, 11(11), 73-81. https://doi.org/10.14569/IJACSA.2020.0111110

Petrović, S., Osborne, M., & Lavrenko, V. (2010). The Edinburgh Twitter corpus. Proceedings of the NAACL HLT 2010 Workshop on Computational Linguistics in a World of Social Media, 25-26. https://aclanthology.org/W10-0513.pdf


Downloads

Downloads per month over past year

Actions (login required)

View Item View Item
Contact us
Send email Sponsors
Sponsor: AIMS Sponsor: D&P Sponsor: UniNa CAB Get connected
Facebook Facebook Twitter Twitter Linkedin LinkedIn RSS RSS