Parallel session 3: Fake, Bias and Hate Speech Detection

Session Chair: Sandra Kübler, Galata hall

10.45-11.10 Looking for Traces of Textual Deepfakes in Bulgarian on Social Media (Irina Temnikova, Iva Marinova, Silvia Gargova, Ruslana Margova and Ivan Koychev)

11.10-11.35 Multi-task Ensemble Learning for Fake Reviews Detection and Helpfulness Prediction: A Novel Approach (Alimuddin Melleng, Anna Jurek-Loughrey and Deepak P)

11.35-12.00 From Fake to Hyperpartisan News Detection Using Domain Adaptation (Răzvan-Alexandru Smădu, Sebastian-Vasile Echim, Dumitru-Clementin Cercel, Iuliana Marin and Florin Pop)

12.00-12.25 Bipol: Multi-axes Evaluation of Bias with Explainability in Benchmark Datasets (Tosin Adewumi, Isabella Södergren, Lama Alkhaled, sana al-azzawi, Foteini Simistira Liwicki and Marcus Liwicki)

12.25-12.50 Exploring Amharic Hate Speech Data Collection and Classification Approaches (Abinew Ali Ayele, Seid Muhie Yimam, Tadesse Destaw Belay, Tesfa Asfaw and Chris Biemann)

12.50-1.15pm Prompt-Based Approach for Czech Sentiment Analysis (Jakub Šmíd and Pavel Přibáň)