Abstract:

In recent years, short videos gained increasing attention as an educational innovation tool (Kruger & Doherty, 2016), mainly due to the widespread adoption and dissemination of short video content on social media (Kaye et al., 2022). Research indicates that short videos are well suited for pedagogical purposes and have the potential to improve learning outcomes (Brame, 2016). In addition, it demonstrates that short videos on social media platforms, such as TikTok, are effective in facilitating knowledge construction (Nguyen & Diederich, 2023).

With the ongoing improvement of the user interface of these platforms, user engagement, manifested through comments and likes, plays a crucial role in informing the development of online instructional courses (Habibi & Salim, 2021). In this context, the current study aims to examine the comments on short videos for learning Portuguese, to gain a deeper understanding of the interests and learning needs of potential Portuguese learners.

This study analysed 32 TikTok videos from an account focusing on teaching European Portuguese. A total of 612 top-level comments were collected in compliance with TikTok's policies. Python-based text mining was used to process the comments and identify topics of interest.

The analysis identified three main clusters from TikTok comments. Cluster #1 revolved around the language learning content, spotlighting words like “speak”, “learn” and “pronounce”, reflecting a focus on oral proficiency and knowledge acquisition. Cluster #2 focused on "Portuguese", with discourse from Brazilian and Spanish speakers about European Portuguese, highlighting perspectives across these linguistic variants. Cluster #3 centred on audience gratitude, indicated by "thank" and related positive terms like "good" and "nice", signalling appreciation for the speaker.

The identification of clusters centred on short instructional videos for Portuguese learners suggests a content inclination towards oral proficiency and the diversity of language development, reflecting learners' interests and pedagogical needs. This provides content creators and practitioners in the area with insights into the types of video content that are more likely to attract and retain viewer engagement.

Acknowledgments:
This work is financially supported by National Funds through FCT – Fundação para a Ciência e a Tecnologia, I.P., under the project 2022.14365.BD, 2021.03379.CEECIND and UIDB/00194/2020.

References:
[1] Brame, C. J. (2016). Effective educational videos: Principles and guidelines for maximizing student learning from video content. CBE Life Sciences Education, 15(4), es6.1-es6.6. https://doi.org/10.1187/cbe.16-03-0125
[2] Habibi, S. A., & Salim, L. (2021). Static vs. dynamic methods of delivery for science communication: A critical analysis of user engagement with science on social media. PLoS ONE, 16(3). https://doi.org/10.1371/journal.pone.0248507
[3] Kaye, D. Bondy. V., Zeng, J., & Wikström, P. (2022). TikTok : creativity and culture in short video. Polity Press.
[4] Kruger, J.-L., & Doherty, S. (2016). Measuring cognitive load in the presence of educational video: Towards a multimodal methodology. Australasian Journal of Educational Technology, 32(6), 19–31. https://doi.org/10.14742/ajet.3084
[5] Nguyen, H., & Diederich, M. (2023). Facilitating knowledge construction in informal learning: A study of TikTok scientific, educational videos. Computers and Education, 205. https://doi.org/10.1016/j.compedu.2023.104896

Keywords:

Short Videos, Text mining, Foreign Language Learning, TikTok.