psytechlab at CLPsych 2026: Utilising Natural Language Processing methods and Large Language Models for Social Media Text Analysis
2026-07-03 • Computation and Language
Computation and Language
AI summaryⓘ
The authors used computer programs that understand language, like LSTM, BERT, and Large Language Models, to analyze social media posts and figure out people's mental health and well-being. They entered a competition where their system did very well in summarizing information consistently and without contradictions. For other related tasks, their results were average. Their work helps build better tools to support mental health, and they shared their code online for others to use.
Natural Language ProcessingLSTMBERTLarge Language ModelsMental Health AnalysisSocial Media DataSummarizationConsistency and ContradictionCLPsych Shared Task
Authors
Igor Buyanov, Nafisa Valieva, Ekaterina Mazurina
Abstract
Social media posts are a rich and valuable source of data for analyzing mental health states and users' well-being using automated analysis tools. In this work, we demonstrate how we used a range of Natural Language Processing (NLP) methods, including Long Short-Term Memory (LSTM), BERT-based models, and Large Language Models (LLMs), for self-state and well-being analysis and summarization during the CLPsych Shared Task 2026. Our approach achieved one of the top Consistency and Contradiction scores for the summarization task and also middle-level results for the other tasks. By testing and developing such mental health-state estimation systems, we contributed to improving mental health support systems. We make our code available https://github.com/psytechlab/CLPsych2026/.