Detecting topics and polarity from Twitter: the ETSII-UPM case
Almudena Sánchez Ruíz, Daniel Galán, Ángel García Beltrán, Javier Rodríguez‐Vidal · Research Square · 2023
Abstract Social networks have become a powerful communication tool, with millions of people exchanging information, opinions and experiences daily. Companies, organizations and even people have turned this tool into a marketing platform to position themselves and gain popularity. However, not only do companies present products or services to society, but society also provides feedback. This feedback has a significant impact as well. It is impossible to process all this vast information manually in time, but it is crucial. This information is precious even for governmental or state public entities such as universities. Potential future students will use social media to find out about the general feel of the institution. Therefore, this study presents a new dataset called CEIMaT2021, which compiles all the tweets in Spanish related to the Technical School of Industrial Engineering of the Universidad Politécnica de Madrid (ETSII-UPM). This dataset is designed for two of the main tasks of Online Reputation Management: (I) automatic detection of topics and (II) polarity. In addition, this study shows for these tasks that the SVM algorithm obtains a better performance for topic detection. Meanwhile, XGB obtains better results for polarity detection.