arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.15470cs.CLcs.AIcs.SI
收藏

基于文本时序表征的精神障碍分类

Mental Disorder Classification via Temporal Representation of Text

Indian Institute of Technology Bombay(印度理工学院孟买分校)

Raja Kumar, Kishan Maharaj, Ashita Saxena, Pushpak Bhattacharyya

AI总结:

针对现有大语言模型处理社交媒体长序列文本预测精神障碍时丢失时序依赖、性能不佳的问题,提出将时序帖子压缩为数字序列的时变表征框架,在三类精神障碍分类上超SOTA,F1提升5%,还开展了跨障碍研究。

摘要:

精神障碍是一项全球性挑战,合格心理健康专业人员的短缺进一步加剧了这一问题。由于序列文本数据的复杂性以及语言模型的上下文长度有限,当前大语言模型(LLM)从社交媒体帖子中预测精神障碍颇具挑战。当前基于语言模型的方法会将单个数据实例拆分为多个块,以弥补上下文大小的限制,随后将预测模型分别应用于每个块,并选取得票最多的输出作为最终预测结果。这会导致帖子间的依赖关系和重要的时变信息丢失,进而造成性能不佳。我们提出了一个新颖的框架,首先将按时间顺序排列的大量社交媒体帖子序列压缩为一系列数字,随后利用这种时变表征进行精神障碍分类。我们在三种不同的精神状况(抑郁症、自残和厌食症)上均优于当前的SOTA(state-of-the-art,当前最优水平),F1分数绝对提升了5%,以此证明了该框架的泛化能力。我们研究了当前数据实例处于语言模型上下文长度范围内的情况,并给出了实证结果,凸显了文本数据时序属性的重要性。此外,我们将所提出的框架用于跨域研究,探索了不同障碍之间的共性以及域间数据使用的可能性。

英文摘要:

Mental disorders pose a global challenge, aggravated by the shortage of qualified mental health professionals. Mental disorder prediction from social media posts by current LLMs is challenging due to the complexities of sequential text data and the limited context length of language models. Current language model-based approaches split a single data instance into multiple chunks to compensate for limited context size. The predictive model is then applied to each chunk individually, and the most voted output is selected as the final prediction. This results in the loss of inter-post dependencies and important time variant information, leading to poor performance. We propose a novel framework which first compresses the large sequence of chronologically ordered social media posts into a series of numbers. We then use this time variant representation for mental disorder classification. We demonstrate the generalization capabilities of our framework by outperforming the current SOTA in three different mental conditions: depression, self-harm, and anorexia, with an absolute improvement of 5% in the F1 score. We investigate the situation where current data instances fall within the context length of language models and present empirical results highlighting the importance of temporal properties of textual data. Furthermore, we utilize the proposed framework for a cross-domain study, exploring commonalities across disorders and the possibility of inter-domain data usage.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑