Current language processing technologies allow the creation of conversational chatbot platforms. Even though artificial intelligence is still too immature to support satisfactory user experience in many mass market domains, interfaces have found their way into ad hoc applications such as call centres and online shopping assistants. However, they not been applied so far social inclusion elderly people, who are particularly vulnerable digital divide. Many them relieve loneliness with...

Previous researchers have proposed intelligent systems for therapeutic monitoring of cognitive impairments. However, most existing practical approaches this purpose are based on manual tests. This raises issues such as excessive caretaking effort and the white-coat effect. To avoid these issues, we present an conversational system entertaining elderly people with news their interest that monitors impairment transparently. Automatic chatbot dialogue stages allow assessing content description...

Abstract Financial news items are unstructured sources of information that can be mined to extract knowledge for market screening applications. They typically written by experts who describe stock events within the context social, economic and political change. Manual extraction relevant from continuous stream finance-related is cumbersome beyond skills many investors, who, at most, follow a few authors. Accordingly, we focus on analysis financial identify text and, text, forecasts...

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 political, sociological cultural factors. the same text, often discusses performance different assets. Some key statements mere descriptions past events while others predictions. Therefore, understanding temporality in a text is essential to separate information from We...

Social media platforms, increasingly used as news sources for varied data analytics, have transformed how information is generated and disseminated. However, the unverified nature of this content raises concerns about trustworthiness accuracy, potentially negatively impacting readers’ critical judgment due to disinformation. This work aims contribute automatic quality validation field, addressing rapid growth online on wiki pages. Our scalable solution includes stream-based processing with...

Artificial intelligence (AI) can potentially transform the industry, enhancing production process and minimizing manual repetitive tasks. Accordingly, synergy between high-performance computing powerful mathematical models enables application of sophisticated data analysis procedures like machine learning (ML). However, challenges exist regarding effective, efficient, flexible processing to generate valuable knowledge. Consequently, this work comprehensively describes industrial where AI be...

Short texts are omnipresent in real-time news, social network commentaries, etc. Traditional text representation methods have been successfully applied to self-contained documents of medium size. However, information short is often insufficient, due, for example, the use mnemonics, which makes them hard classify. Therefore, particularities specific domains must be exploited. In this article we describe a novel system that combines Natural Language Processing techniques with Machine Learning...

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 stock markets in real-time and, often, influencing this state. We interested user forecasts financial, social media messages expressing opportunities precautions about assets. propose novel Targeted Aspect-Based Emotion...

Material extrusion is one of the most commonly used approaches within additive manufacturing processes available. Despite its popularity and related technical advancements, process reliability quality assurance remain only partially solved. In particular, surface roughness caused by this a key concern. To solve constraint, experimental plans have been exploited to optimize in recent years. However, latter empirical trial error extremely time- resource-consuming. Thus, study aims avoid using...

Data crowdsourcing is a data acquisition process where groups of voluntary contributors feed platforms with highly relevant ranging from news, comments, and media to knowledge classifications. It typically processes user-generated streams provide refine popular services such as wikis, collaborative maps, e-commerce sites, social networks. Nevertheless, this modus operandi raises severe concerns regarding ill-intentioned manipulation in adversarial environments. This paper presents...

Automatic legal text classification systems have been proposed in the literature to address knowledge extraction from judgments and detect their aspects. However, most of these are black boxes even when models interpretable. This may raise concerns about trustworthiness. Accordingly, this work contributes with a system combining Natural Language Processing (NLP) Machine Learning (ML) classify texts an explainable manner. We analyze features involved decision threshold bifurcation values...

Social media platforms enable the rapid dissemination and consumption of information. However, users instantly consume such content regardless reliability shared data. Consequently, latter crowdsourcing model is exposed to manipulation. This work contributes with an explainable online classification method recognize fake news in real-time. The proposed combines both unsupervised supervised Machine Learning approaches created lexica. profiling built using creator-, content- context-based...

Social media include diverse interaction metrics related to user popularity, the most evident example being number of followers. The latter has raised concerns about credibility posts by popular creators. However, existing approaches assess in social strictly consider this problem a binary classification, often based on priori information, without checking if actual real-world facts back users' comments. In addition, they do not provide automatic explanations their predictions foster...

In recent years, the field of Natural Language Generation (NLG) has been boosted by advances in deep learning technologies. Nonetheless, these new data-intensive methods introduce language-dependent disparities NLG as main training data sets are English. Also, most neural systems use decoder-only (causal) transformer language models, which work well for English, but were not designed with other languages mind. this we depart from hypothesis that they may generation bias target less rigid...

Based on official estimates, 50 million people worldwide are affected by dementia, and this number increases 10 new patients every year. Without a cure, clinical prognostication early intervention represent the most effective ways to delay its progression. To end, Artificial Intelligence computational linguistics can be exploited for natural language analysis, personalized assessment, monitoring, treatment. However, traditional approaches need more semantic knowledge management explicability...

Micro-blogging sources such as the Twitter social network provide valuable real-time data for market prediction models. Investors' opinions in this follow fluctuations of stock markets and often include educated speculations on opportunities that may have impact actions other investors. In view this, we propose a novel system to detect positive predictions tweets, type financial emotions which term "opportunities" are akin "anticipation" Plutchik's theory. Specifically, seek high detection...