Identifying changes in individuals’ behaviour and mood, as observed via content shared on online platforms, is increasingly gaining importance. Most research to-date on this topic focuses on either: (a) identifying individuals at risk or with a certain mental health condition given a batch of posts or (b) providing equivalent labels at the post level. A disadvantage of such work is the lack of a strong temporal component and the inability to make longitudinal assessments following an individual’s trajectory and allowing timely interventions. Here we define a new task, that of identifying moments of change in individuals on the basis of their shared content online. The changes we consider are sudden shifts in mood (switches) or gradual mood progression (escalations). We have created detailed guidelines for capturing moments of change and a corpus of 500 manually annotated user timelines (18.7K posts). We have developed a variety of baseline models drawing inspiration from related tasks and show that the best performance is obtained through context aware sequential modelling. We also introduce new metrics for capturing rare events in temporal windows.

We introduce the task of microblog opinion summarization (MOS) and share a dataset of 3100 gold-standard opinion summaries to facilitate research in this domain. The dataset contains summaries of tweets spanning a 2-year period and covers more topics than any other public Twitter summarization dataset. Summaries are abstractive in nature and have been created by journalists skilled in summarizing news articles following a template separating factual information (main story) from author opinions. Our method differs from previous work on generating gold-standard summaries from social media, which usually involves selecting representative posts and thus favors extractive summarization models. To showcase the dataset’s utility and challenges, we benchmark a range of abstractive and extractive state-of-the-art summarization models and achieve good performance, with the former outperforming the latter. We also show that fine-tuning is necessary to improve performance and investigate the benefits of using different sample sizes.

We provide an overview of the CLPsych 2022 Shared Task, which focusses on the automatic identification of ‘Moments of Change’ in lon- gitudinal posts by individuals on social media and its connection with information regarding mental health . This year’s task introduced the notion of longitudinal modelling of the text generated by an individual online over time, along with appropriate temporally sen- sitive evaluation metrics. The Shared Task con- sisted of two subtasks: (a) the main task of cap- turing changes in an individual’s mood (dras- tic changes-‘Switches’- and gradual changes -‘Escalations’- on the basis of textual content shared online; and subsequently (b) the sub- task of identifying the suicide risk level of an individual – a continuation of the CLPsych 2019 Shared Task– where participants were encouraged to explore how the identification of changes in mood in task (a) can help with assessing suicidality risk in task (b).

We present the first work on automatically capturing alliance rupture in transcribed therapy sessions, trained on the text and self-reported rupture scores from both therapists and clients. Our NLP baseline outperforms a strong majority baseline by a large margin and captures client reported ruptures unidentified by therapists in 40% of such cases.

Collecting together microblogs representing opinions about the same topics within the same timeframe is useful to a number of different tasks and practitioners. A major question is how to evaluate the quality of such thematic clusters. Here we create a corpus of microblog clusters from three different domains and time windows and define the task of evaluating thematic coherence. We provide annotation guidelines and human annotations of thematic coherence by journalist experts. We subsequently investigate the efficacy of different automated evaluation metrics for the task. We consider a range of metrics including surface level metrics, ones for topic model coherence and text generation metrics (TGMs). While surface level metrics perform well, outperforming topic coherence metrics, they are not as consistent as TGMs. TGMs are more reliable than all other metrics considered for capturing thematic coherence in microblog clusters due to being less sensitive to the effect of time windows.

Semantic change detection concerns the task of identifying words whose meaning has changed over time. Current state-of-the-art approaches operating on neural embeddings detect the level of semantic change in a word by comparing its vector representation in two distinct time periods, without considering its evolution through time. In this work, we propose three variants of sequential models for detecting semantically shifted words, effectively accounting for the changes in the word representations over time. Through extensive experimentation under various settings with synthetic and real data we showcase the importance of sequential modelling of word vectors through time for semantic change detection. Finally, we compare different approaches in a quantitative manner, demonstrating that temporal modelling of word representations yields a clear-cut advantage in performance.

Semantic change detection (i.e., identifying words whose meaning has changed over time) started emerging as a growing area of research over the past decade, with important downstream applications in natural language processing, historical linguistics and computational social science. However, several obstacles make progress in the domain slow and difficult. These pertain primarily to the lack of well-established gold standard datasets, resources to study the problem at a fine-grained temporal resolution, and quantitative evaluation approaches. In this work, we aim to mitigate these issues by (a) releasing a new labelled dataset of more than 47K word vectors trained on the UK Web Archive over a short time-frame (2000-2013); (b) proposing a variant of Procrustes alignment to detect words that have undergone semantic shift; and (c) introducing a rank-based approach for evaluation purposes. Through extensive numerical experiments and validation, we illustrate the effectiveness of our approach against competitive baselines. Finally, we also make our resources publicly available to further enable research in the domain.

We present a system for time sensitive, topic based summarisation of the sentiment around target entities and topics in collections of tweets. We describe the main elements of the system and illustrate its functionality with two examples of sentiment analysis of topics related to the 2017 UK general election.

In this paper we address a new problem of predicting affect and well-being scales in a real-world setting of heterogeneous, longitudinal and non-synchronous textual as well as non-linguistic data that can be harvested from on-line media and mobile phones. We describe the method for collecting the heterogeneous longitudinal data, how features are extracted to address missing information and differences in temporal alignment, and how the latter are combined to yield promising predictions of affect and well-being on the basis of widely used psychological scales. We achieve a coefficient of determination (R²) of 0.71-0.76 and a correlation coefficient of 0.68-0.87 which is higher than the state-of-the art in equivalent multi-modal tasks for affect.