Représentations lexicales pour la détection non supervisée d'événements dans un flux de tweets : étude sur des corpus français et anglais
This work addresses event detection for social media analysis, but it is incremental as it primarily compares existing methods without introducing a new paradigm.
The paper tackled unsupervised event detection in tweet streams by evaluating recent text embeddings like ELMo and BERT, finding that tf-idf approaches outperformed these deep learning methods, with experiments showing concrete performance gaps on French and English datasets.
In this work, we evaluate the performance of recent text embeddings for the automatic detection of events in a stream of tweets. We model this task as a dynamic clustering problem.Our experiments are conducted on a publicly available corpus of tweets in English and on a similar dataset in French annotated by our team. We show that recent techniques based on deep neural networks (ELMo, Universal Sentence Encoder, BERT, SBERT), although promising on many applications, are not very suitable for this task. We also experiment with different types of fine-tuning to improve these results on French data. Finally, we propose a detailed analysis of the results obtained, showing the superiority of tf-idf approaches for this task.