Bruke sentimentanalyse for lingvistikkforskning: Tanker fra eksperimentell forskning på moderne italiensk
Forskergruppen LDLC inviterer til gjesteforelesning. Del gjerne invitasjonen med potensielt interesserte kollegaer og studenter som ikke står på IF eller LLE sine e-postlister!
Lorella Viola (University of Luxembourg), 'Using sentiment analysis for linguistics research: Thoughts from experimental research in contemporary Italian'
Annotating textual material for attitudes – either sentiment or opinions – through a method called sentiment analysis (SA) is a technique that can add value to digital material. This method aims to identify the prevailing emotional attitude in a given text, though it often remains unclear whether the method detects the attitude of the writer or the expressed polarity in the analyzed textual fragment.
An SA task is usually modeled as a classification problem, that is a classifier processes pre-defined elements in a text (e.g., sentences) and it returns a category (e.g., positive, negative, or neutral).
In this presentation, I will discuss the limitations and advantages of using SA for linguistics research. Specifically, using contemporary social media discourse in Italian as a case study and Twitter as data source, I will unpack the assumptions and misconceptions behind this technique and discuss the implications of its use in domains of research that transcend the method’s original conception.
About the speaker:
Dr Viola is a Research Associate at the Luxembourg Centre for Contemporary and Digital History (C2DH), University of Luxembourg. Her research focuses on how power, latent assumptions and implicit ideologies are manifested through language and circulated in media and society. She also investigates the impact of the digital transformation of society on knowledge creation theory and practice and devises critical, data-driven methodologies for humanities and heritage research. Her new book The Humanities in the Digital will be published in December 2022 (Springer – Palgrave MacMillan).