Prof. Kobi Gal

We present our approach to Task 1 of the CLEF eRisk 2025 Lab, which focuses on identifying depression symptoms in user-generated text. The task is formulated as a sentence ranking problem, aiming to retrieve sentences relevant to each of the 21 symptoms defined in the Beck Depression Inventory-II (BDI-II). The method employs Sentence-BERT to compute semantic similarity between user text and symptom queries derived from the BDI questionnaire’s multiple-choice responses. To improve coverage, queries are expanded based on retrieval results from the training set. Additionally, sentences not referring to the user are filtered out to reduce noise from third-person narratives. Our approach achieved competitive performance, with Average Precision substantially exceeding the median of all submitted systems. This demonstrates the promise of semantic retrieval and first-person filtering for identifying fine-grained depressive symptoms at scale.