Social media provides valuable insights into users' thoughts, behaviors, and emotions, offering opportunities for mental health research. In this work, we explore how personality traits and demographic attributes manifest in the online behavior of individuals suffering from mental disorders. Focusing on the Big-5 personality dimensions, we analyze social media users associated with four mental health disorders (Anorexia, Depression, Gambling, and Self-harm), investigating how these traits differ across groups. Using the PANDORA dataset –which provides annotations for personality traits, age, and gender–, we train models for personality prediction and author profiling. These models are subsequently transferred to various eRisk collections. Besides confirming known trends (e.g., high association between anorexia and certain young female groups, or between gambling and young males), our analysis reveals intriguing personality traits. For example, we found high neuroticism and agreeableness, and low extraversion and conscientiousness shared across most disorders. These trends underscore the relevance of these personality traits for these mental health problems. Finally, we conclude by analyzing demographic biases in risk detection systems and show that alert accuracy differs significantly across demographic groups.

Misinformation on the Internet poses significant risks to users seeking health information.This paper addresses the challenge of generating effective health-related queries to promote reliable search results.We propose a method leveraging Large Language Models to generate synthetic narratives that guide the creation of alternative queries.These queries are designed to retrieve more helpful and fewer harmful documents compared to those retrieved by the original user queries.We evaluate the effectiveness of these queries using classic and neural retrieval models across multiple datasets, demonstrating promising improvements in retrieving reputable content.

While it is often assumed that searching for information to evaluate misinformation will help identify false claims, recent work suggests that search behaviours can instead reinforce belief in misleading news, particularly when users generate queries using vocabulary from the source articles. Our research explores how different query generation strategies affect news verification and whether the way people search influences the accuracy of their information evaluation. A mixed-methods approach was used, consisting of three parts: (1) an analysis of existing data to understand how search behaviour influences trust in fake news (2) a simulation of query generation strategies using a Large Language Model (LLM) to assess the impact of different query formulations on search result quality, and (3) a user study to examine how 'Boost' interventions in interface design can guide users to adopt more effective query strategies. The results show that search behaviour significantly affects trust in news, with successful searches involving multiple queries and yielding higher-quality results. Queries inspired by different parts of a news article produced search results of varying quality, and weak initial queries improved when reformulated using full SERP information. Although 'Boost' interventions had limited impact, the study suggests that interface design encouraging users to thoroughly review search results can enhance query formulation. This study highlights the importance of query strategies in evaluating news and proposes that interface design can play a key role in promoting more effective search practices, serving as one component of a broader set of interventions to combat misinformation.

Abstract The COVID-19 pandemic, a global contagion of coronavirus infection caused by Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2), has triggered severe social and economic disruption around the world and provoked changes in people’s behavior. Given the extreme societal impact of COVID-19, it becomes crucial to understand the emotional response of the people and the impact of COVID-19 on personality traits and psychological dimensions. In this study, we contribute to this goal by thoroughly analyzing the evolution of personality and psychological aspects in a large-scale collection of tweets extracted during the COVID-19 pandemic. The objectives of this research are: i) to provide evidence that helps to understand the estimated impact of the pandemic on people’s temperament, ii) to find associations and trends between specific events (e.g., stages of harsh confinement) and people’s reactions, and iii) to study the evolution of multiple personality aspects, such as the degree of introversion or the level of neuroticism. We also examine the development of emotions, as a natural complement to the automatic analysis of the personality dimensions. To achieve our goals, we have created two large collections of tweets (geotagged in the United States and Spain, respectively), collected during the pandemic. Our work reveals interesting trends in personality dimensions, emotions, and events. For example, during the pandemic period, we found increasing traces of introversion and neuroticism. Another interesting insight from our study is that the most frequent signs of personality disorders are those related to depression, schizophrenia, and narcissism. We also found some peaks of negative/positive emotions related to specific events.

Abstract The availability of large web-based corpora has led to significant advances in a wide range of technologies, including massive retrieval systems or deep neural networks. However, leveraging this data is challenging, since web content is plagued by the so-called boilerplate: ads, incomplete or noisy text and rests of the navigation structure, such as menus or navigation bars. In this work, we present a novel and efficient approach to extract useful and well-formed content from web-scraped data. Our approach takes advantage of Language Models and their implicit knowledge about correctly formed text, and we demonstrate here that perplexity is a valuable artefact that can contribute in terms of effectiveness and efficiency. As a matter of fact, the removal of noisy parts leads to lighter AI or search solutions that are effective and entail important reductions in resources spent. We exemplify here the usefulness of our method with two downstream tasks, search and classification, and a cleaning task. We also provide a Python package with pre-trained models and a web demo demonstrating the capabilities of our approach.

Determining reliability of online data is a challenge that has recently received increasing attention. In particular, unreliable health-related content has become pervasive during the COVID-19 pandemic. The main objective of this Ph.D. thesis is to study how end-users judge the correctness and credibility of online content and provide them with a series of tools to assist them in assessing content reliability. To that end, we need to determine which sources of evidence may help to better assess the reliability of health-related online content, and how to combine them learning. Finally, I will also study which presentation aspects might help end-users to better assess reliability since previous research has proved that the format and layout of the information items, combined with user-based biases, influence their final assessments.