Fakultät für Technische Wissenschaften
Social media are computer-based technologies that provide means of information and idea sharing, as well as entertainment and engagement handly available as mobile applications and websites to both private users and businesses. As social media communication is mostly informal, it is an ideal environment for the use of emoji and for detecting the population’s sentiments and stance. Sentiment* and stance** analysis have been heavily researched in the last decade and the technology to address these data analysis tasks have developed rapidly. In this talk, several inspiring sentiment and stance analysis applications will be presented, varying in data source, topics, language, and approaches used. As a result of several years of experience in sentiment and stance analysis, best practices guidelines will be provided and remaining challenges exposed.
*Sentiment analysis is the field of study that analyzes people’s opinions, sentiments, evaluations, attitudes, and emotions from a text.
**Stance analysis is the task of automatically determining from text whether the author of the text is in favor of, against, or neutral towards a proposition or target.
Dr. Petra Kralj Novak
Christian Timmerer (christian [dot] timmerer [at] itec [dot] aau [dot] at)