ABSTRACT Mental well‐being is a worldwide priority of health systems. Nevertheless, the diagnosis and recovery rates are still low. This work demonstrates an Artificial Intelligence (AI)‐based, entertainment‐oriented, engaging assistant that can deliver on‐demand, non‐judgmental assessment in an accessible, scalable, and personalised way to people affected by anxiety and depression. For this purpose, we combine Machine Learning (ML) and Large Language Models (LLMs) in a stream‐based framework. Here, the LLMs are exploited to extract high‐level reasoning features from natural language utterances for an accurate ML prediction model. During a study lasting for 14 months, the participants, 146 users mostly within the 65–80 age range, used the conversational assistant. Each user was free to participate as they pleased, with average individual activity times of 4.5 months. During their participation, each user completed an average of two standard mental condition tests, which allowed updating the mental condition tags for classifier retraining in streaming mode. Our solution achieved promising results for detecting anxiety and depression in free dialogues, with accuracy metrics exceeding 90%, outperforming competing works from the literature. Moreover, prior research on anxiety and depression detection has often been limited to providing binary outcomes without explanations behind their rationale. Therefore, this work also addresses interpretability by automatically explaining its prediction in natural language. The contributions of this work are threefold: (i) detecting mental conditions from free dialogues in real‐time with minimal supervision, (ii) conducting a non‐invasive longitudinal analysis based on user engagement, and (iii) automatically providing explanations of the predictive capabilities of the solution. Our approach, supporting continuous interactions suitable for longitudinal studies, combined with explainability mechanisms, connects directly with several strategic lines promoted by the European Union (EU). In particular, the emphasis on early prevention and detection is aligned with a conversational tool that monitors indicators over time. Similarly, the EU promotes transparency, ethical governance, and trust in digital health technologies, as well as data interoperability and common standards as part of the push toward the European Health Data Space. In this context, incorporating explainability, that is, providing the user or researcher with understandable reasons for the model's inferences, strengthens acceptability, accountability, and alignment with good digital governance principles. In this way, our approach contributes to translating the European objectives of promoting accessible, safe, ethical, and evidence‐based digital mental health tools into practice, while facilitating longitudinal monitoring and proactive intervention.

Natural Language Generation ( nlg ) popularity has increased owing to the progress in Large Language Models ( llm s), with zero-shot inference capabilities. However, most neural systems utilize decoder-only causal (unidirectional) transformer models, which are effective for English but may reduce the richness of languages with less strict word order, subject omission, or different relative clause attachment preferences. This is the first work that analytically addresses optimal text generation order for non-causal language models . We present a novel Viterbi algorithm-based methodology for maximum likelihood word order estimation. We analyze the non-causal most-likelihood order probability for nlg in Spanish and, then, the probability of generating the same phrases with Spanish causal nlg . This comparative analysis reveals that causal nlg prefers English-like svo structures. We also analyze the relationship between optimal generation order and causal left-to-right generation order using Spearman’s rank correlation. Our results demonstrate that the ideal order predicted by the maximum likelihood estimator is not closely related to the causal order and may be influenced by the syntactic structure of the target sentence.

Abstract Cognitive and neurological impairments are very common, but only a small proportion of affected individuals are diagnosed and treated, partly because of the high costs associated with frequent screening. Detecting pre-illness stages and analyzing the progression of neurological disorders through effective and efficient intelligent systems can be beneficial for timely diagnosis and early intervention. We propose using Large Language Models to extract features from free dialogues to detect cognitive decline. These features comprise high-level reasoning content-independent features (such as comprehension, decreased awareness, increased distraction, and memory problems). Our solution comprises (i) preprocessing, (ii) feature engineering via Natural Language Processing techniques and prompt engineering, (iii) feature analysis and selection to optimize performance, and (iv) classification, supported by automatic explainability. We also explore how to improve Chatgpt’s direct cognitive impairment prediction capabilities using the best features in our models. Evaluation metrics obtained endorse the effectiveness of a mixed approach combining feature extraction with Chatgpt and a specialized Machine Learning model to detect cognitive decline within free-form conversational dialogues with older adults. Ultimately, our work may facilitate the development of an inexpensive, non-invasive, and rapid means of detecting and explaining cognitive decline.

Social media include diverse interaction metrics related to user popularity, the most evident example being the number of user followers. The latter has raised concerns about the credibility of the posts by the most popular creators. However, most existing approaches to assess credibility in social media strictly consider this problem a binary classification, often based on a priori information, without checking if actual real-world facts back the users’ comments. In addition, they do not provide automatic explanations of their predictions to foster their trustworthiness. In this work, we propose a credibility assessment solution for financial creators in social media that combines Natural Language Processing and Machine Learning. The reputation of the contributors is assessed by automatically classifying their forecasts on asset values by type and verifying these predictions with actual market data to approximate their probability of success. The outcome of this verification is a continuous credibility score instead of a binary result, an entirely novel contribution by this work. Moreover, social media metrics (i.e., user context) are exploited by calculating their correlation with the credibility rankings, providing insights on the interest of the end-users in financial posts and their forecasts (i.e., drop or rise). Finally, the system provides natural language explanations of its decisions based on a model-agnostic analysis of relevant features.

Abstract Social media platforms enable the rapid dissemination and consumption of information. However, users instantly consume such content regardless of the reliability of the shared data. Consequently, the latter crowdsourcing model is exposed to manipulation. This work contributes with an explainable and online classification method to recognize fake news in real-time. The proposed method combines both unsupervised and supervised Machine Learning approaches with online created lexica. The profiling is built using creator-, content- and context-based features using Natural Language Processing techniques. The explainable classification mechanism displays in a dashboard the features selected for classification and the prediction confidence. The performance of the proposed solution has been validated with real data sets from Twitter and the results attain 80% accuracy and macro F-measure. This proposal is the first to jointly provide data stream processing, profiling, classification and explainability. Ultimately, the proposed early detection, isolation and explanation of fake news contribute to increase the quality and trustworthiness of social media contents.

Abstract Financial news items are unstructured sources of information that can be mined to extract knowledge for market screening applications. They are typically written by market experts who describe stock market events within the context of social, economic and political change. Manual extraction of relevant information from the continuous stream of finance-related news is cumbersome and beyond the skills of many investors, who, at most, can follow a few sources and authors. Accordingly, we focus on the analysis of financial news to identify relevant text and, within that text, forecasts and predictions. We propose a novel Natural Language Processing (nlp) system to assist investors in the detection of relevant financial events in unstructured textual sources by considering both relevance and temporality at the discursive level. Firstly, we segment the text to group together closely related text. Secondly, we apply co-reference resolution to discover internal dependencies within segments. Finally, we perform relevant topic modelling with Latent Dirichlet Allocation (lda) to separate relevant from less relevant text and then analyse the relevant text using a Machine Learning-oriented temporal approach to identify predictions and speculative statements. Our solution outperformed a rule-based baseline system. We created an experimental data set composed of 2,158 financial news items that were manually labelled by nlp researchers to evaluate our solution. Inter-agreement Alpha-reliability and accuracy values, and rouge-l results endorse its potential as a valuable tool for busy investors. The rouge-l values for the identification of relevant text and predictions/forecasts were 0.662 and 0.982, respectively. To our knowledge, this is the first work to jointly consider relevance and temporality at the discursive level. It contributes to the transfer of human associative discourse capabilities to expert systems through the combination of multi-paragraph topic segmentation and co-reference resolution to separate author expression patterns, topic modelling with lda to detect relevant text, and discursive temporality analysis to identify forecasts and predictions within this text. Our solution may have compelling applications in the financial field, including the possibility of extracting relevant statements on investment strategies to analyse authors’ reputations.

Microblogging platforms, of which Twitter is a representative example, are valuable information sources for market screening and financial models. In them, users voluntarily provide relevant information, including educated knowledge on investments, reacting to the state of the stock markets in real-time and, often, influencing this state. We are interested in the user forecasts in financial, social media messages expressing opportunities and precautions about assets. We propose a novel Targeted Aspect-Based Emotion Analysis (TABEA) system that can individually discern the financial emotions (positive and negative forecasts) on the different stock market assets in the same tweet (instead of making an overall guess about that whole tweet). It is based on Natural Language Processing (NLP) techniques and Machine Learning streaming algorithms. The system comprises a constituency parsing module for parsing the tweets and splitting them into simpler declarative clauses; an offline data processing module to engineer textual, numerical and categorical features and analyse and select them based on their relevance; and a stream classification module to continuously process tweets on-the-fly. Experimental results on a labelled data set endorse our solution. It achieves over 90% precision for the target emotions, financial opportunity, and precaution on Twitter. To the best of our knowledge, no prior work in the literature has addressed this problem despite its practical interest in decision-making, and we are not aware of any previous NLP nor online Machine Learning approaches to TABEA.

Finance-related news such as Bloomberg News, CNN Business and Forbes are valuable sources of real data for market screening systems. In news, an expert shares opinions beyond plain technical analyses that include context such as political, sociological and cultural factors. In the same text, the expert often discusses the performance of different assets. Some key statements are mere descriptions of past events while others are predictions. Therefore, understanding the temporality of the key statements in a text is essential to separate context information from valuable predictions. We propose a novel system to detect the temporality of finance-related news at discourse level that combines Natural Language Processing and Machine Learning techniques, and exploits sophisticated features such as syntactic and semantic dependencies. More specifically, we seek to extract the dominant tenses of the main statements, which may be either explicit or implicit. We have tested our system on a labelled dataset of finance-related news annotated by researchers with knowledge in the field. Experimental results reveal a high detection precision compared to an alternative rule-based baseline approach. Ultimately, this research contributes to the state-of-the-art of market screening by identifying predictive knowledge for financial decision making.

Emoji sentiment analysis is a relevant research topic nowadays, for which emoji sentiment lexica are key assets.Manual annotation affects directly their quality (where high quality usually corresponds to high self-agreement and interagreement).In this work we present an unsupervised methodology to evaluate emoji sentiment lexica generated from online resources, based on a correlation analysis between a gold standard and the scores resulting from the sentiment analysis of the emoji descriptions in those resources.We consider in our study four such online resources of emoji descriptions: Emojipedia, Emojis.wiki,CLDR emoji character annotations and iEmoji.These resources provide knowledge about real (intended) emoji meanings from different author approaches and perspectives.We also present the automatic creation of a joint lexicon where the sentiment of a given emoji is obtained by averaging its scores from the unsupervised analysis of all the resources involved.The results for the joint lexicon are highly promising, suggesting that valuable subjective information can be inferred from authors' descriptions in online resources.

In recent years, social media have been intensively analyzed using sentiment analysis in order to support marketing campaigns.However, when monitoring major public events, social media users' behavior may be strongly biased by the actions of the characters in an event and by a sense of group belonging, typically linked to a specific geographical area.For an event with worldwide impact, we describe a novel solution to automatically assessing the engagement of social media users that combines a location estimation procedure with an unsupervised sentiment analysis technique.The location estimation procedure, which is content-agnostic and applies a network model based on follower accounts, is competitive with previous solutions or outperforms them.The unsupervised sentiment analysis technique, based on language semantics, achieves quite satisfactory results, bearing in mind that, unlike supervised systems, it does not require domain-specific training using annotated text.As far as we are aware, this is the first time these techniques have been implemented jointly.We demonstrate that our solution is coherent with the intrinsic predisposition of users towards the actions of the characters in an event and with a sense of group belonging.