Laskennalliset tieteet Suomen yliopistoissa vuonna 2021

Implementing sentiment analysis to an open-ended questionnaire: Case study of digitalization in elderly care during COVID-19

[EN] The rise of digital technology has enabled us to utilize even more integrated systems for social and health care, but these systems are often complex and time-consuming to learn for the end users without relevant training or experience. We aim to perform Named Entity Recognition based sentiment analysis using the answers of eldercare workers that have taken a survey about the effects of digitalization on their work. The collection of the panel survey data was carried out in two waves: in 2019 and 2021. For the sentiment analysis we compare these two waves to determine the effects of COVID-19 on the work of eldercare workers. The research questions we ask are the following: “Has technol…

Kuntoutuskurssille osallistuneiden avanneleikattujen liikunnan harrastaminen ja fyysinen kunto

Dealing with a small amount of data : developing Finnish sentiment analysis

Sentiment analysis has been more and more prominently visible among all natural language processing tasks. Sentiment analysis entails information extraction of opinions, emotions, and sentiments. In this paper, we aim to develop and test language models for low-resource language Finnish. We use the term “low-resource” to describe a language lacking in available resources for language modeling, especially annotated data. We investigate four models: the state-of-the-art FinBERT [1], and competitive alternative BERT models Finnish ConvBERT [2], Finnish Electra [3], and Finnish RoBERTa [4]. Having a comparative framework of multiple BERT variations is connected to our use of additional methods …

Understanding Twitch Esports Communities through Livestream Chat Analysis