Hate speech and topic shift in the covid-19 public discourse on social media in Italy

The availability of large annotated corpora from social media and the development of powerful classification approaches have contributed in an unprecedented way to tackle the challenge of monitoring users' opinions and sentiments in online social platforms across time but also arose the challenge of temporal robustness of such detection and monitoring systems. We used as case study a dataset of tweets in Italian related to the COVID-19 induced lockdown in Italy to measure how quickly the most debated topic online shifted in time. We concluded that it is a promising approach but dedicated corpora and fine tuning of algorithms are crucial for more insightful results.