Search Results (21)

This study addresses the ongoing challenge of optimizing chatbot interactions to significantly enhance customer experience and satisfaction through personalized, empathetic responses. Using advanced NLP tools and strong statistical methodologies, we developed and evaluated a multi-layered analytical framework to accurately identify user intents, assess customer feedback, and generate emotionally intelligent interactions. With over 270,000 customer chatbot interaction records in our dataset, we employed spaCy-based NER and clustering algorithms (HDBSCAN and K-Means) to categorize customer queries precisely. Text classification was performed using random forest, logistic regression, and SVM, achieving near-perfect accuracy. Sentiment analysis was conducted using VADER, Naive Bayes, and TextBlob, complemented by semantic analysis via LDA. Statistical tests, including Chi-square, Kruskal–Wallis, Dunn’s test, ANOVA, and logistic regression, confirmed the significant impact of tailored, empathetic response strategies on customer satisfaction. Correlation analysis indicated that traditional measures like sentiment polarity and text length insufficiently capture customer satisfaction nuances. The results underscore the critical role of context-specific adjustments and emotional responsiveness, paving the way for future research into chatbot personalization and customer-centric system optimization. Full article

The absence of parental presence has a direct impact on the emotional stability and social routines of children, especially during extended periods of separation from their family environment, as in the case of daycare centers, hospitals, or when they remain alone at home. At the same time, the technology currently available to provide emotional support in these contexts remains limited. In response to the growing need for emotional support and companionship in child care, this project proposes the development of a multi-platform software architecture based on artificial intelligence (AI), designed to be integrated into humanoid robots that assist children between the ages of 6 and 14. The system enables daily verbal and non-verbal interactions intended to foster a sense of presence and personalized connection through conversations, games, and empathetic gestures. Built on the Robot Operating System (ROS), the software incorporates modular components for voice command processing, real-time facial expression generation, and joint movement control. These modules allow the robot to hold natural conversations, display dynamic facial expressions on its LCD (Liquid Crystal Display) screen, and synchronize gestures with spoken responses. Additionally, a graphical interface enhances the coherence between dialogue and movement, thereby improving the quality of human–robot interaction. Initial evaluations conducted in controlled environments assessed the system’s fluency, responsiveness, and expressive behavior. Subsequently, it was implemented in a pediatric hospital in Guayaquil, Ecuador, where it accompanied children during their recovery. It was observed that this type of artificial intelligence-based software, can significantly enhance the experience of children, opening promising opportunities for its application in clinical, educational, recreational, and other child-centered settings. Full article

Cultural heritage institutions, such as museums and galleries, today face the challenge of managing an increasing volume of unsolicited visitor feedback generated across online platforms. This study offers a practical and scalable methodology that transforms 5856 multilingual Google reviews from 59 globally ranked museums and galleries into actionable insights through sentiment analysis, correlation diagnostics, and guided Latent Dirichlet Allocation. By addressing the limitations of prior research, such as outdated datasets, monolingual bias, and narrow geographical focus, the authors analyze a current and diverse set of recent reviews to capture a timely and globally relevant perspective on visitor experiences. The adopted guided LDA model identifies 12 key topics, reflecting both operational issues and emotional responses. The results indicate that while visitors generally express overwhelmingly positive sentiments, dissatisfaction tends to be concentrated in specific service areas. Correlation analysis reveals that longer, emotionally rich reviews are more likely to convey stronger sentiment and receive peer endorsement, highlighting their diagnostic significance. From a practical perspective, the methodology empowers professionals to prioritize improvements based on data-driven insights. By integrating quantitative metrics with qualitative topics, this study supports operational decision-making and cultivates a more empathetic and responsive data management mindset for museums. The reproducible and adaptable nature of the pipeline makes it suitable for cultural institutions of various sizes and resources. Ultimately, this work contributes to the field of cultural informatics by bridging computational precision with humanistic inquiry. That is, it illustrates how intelligent analysis of visitor reviews can lead to a more personalized, inclusive, and strategic museum experience. Full article

Empathetic response generation stands as a pivotal endeavor in the development of human-like dialogue systems. An effective approach in previous research is integrating external knowledge to generate empathetic responses. However, existing approaches only focus on identifying a user’s current emotional state, and they overlook the user’s emotional transition during context, and fail to propel the sustainability of the dialogue. To tackle the aforementioned issues, we propose an empathetic response generation model based on an emotional transition prompt and dual-semantic contrastive learning (EPDC). Specifically, we first compute the transition in users’ sentiment polarity during the conversation and incorporate it into the conversation embedding as sentiment prompts. Then, we generate two distinct fine-grained contextual representations and treat them as positive examples for contrastive learning, respectively, aiming at extracting high-order semantic information to guide the subsequent turn of dialogue. Finally, we also leverage commonsense knowledge to enhance the contextual representations, and the empathetic responses are generated by decoding the combination of semantic and emotional states. Notably, our work represents the pioneering application of emotional prompts and contrastive learning to augment the sustainability of empathetic dialogue. Extensive experiments conducted on the benchmark dataset EMPATHETICDIALOGUES demonstrate that EPDC outperforms the baselines in both automatic evaluations and human evaluations. Full article

Background: Large language models (LLMs) such as ChatGPT, Google Gemini, and Microsoft Copilot are increasingly used by patients seeking medical information online. While these tools provide accessible and conversational explanations, their accuracy and safety in emotionally sensitive scenarios—such as an incidental cancer diagnosis—remain uncertain. Objective: To evaluate the quality, completeness, readability, and safety of responses generated by three state-of-the-art LLMs to common patient questions following the incidental discovery of a kidney tumor. Methods: A standardized use-case scenario was developed: a patient learns of a suspicious renal mass following a computed tomography (CT) scan for back pain. Ten plain-language prompts reflecting typical patient concerns were submitted to ChatGPT-4o, Microsoft Copilot, and Google Gemini 2.5 Pro without additional context. Responses were independently assessed by five board-certified urologists using a validated six-domain rubric (accuracy, completeness, clarity, currency, risk of harm, hallucinations), scored on a 1–5 Likert scale. Two statistical approaches were applied to calculate descriptive scores and inter-rater reliability (Fleiss’ Kappa). Readability was analyzed using the Flesch Reading Ease (FRE) and Flesch–Kincaid Grade Level (FKGL) metrics. Results: Google Gemini 2.5 Pro achieved the highest mean ratings across most domains, notably in accuracy (4.3), completeness (4.3), and low hallucination rate (4.6). Microsoft Copilot was noted for empathetic language and consistent disclaimers but showed slightly lower clarity and currency scores. ChatGPT-4o demonstrated strengths in conversational flow but displayed more variability in clinical precision. Overall, 14% of responses were flagged as potentially misleading or incomplete. Inter-rater agreement was substantial across all domains (κ = 0.68). Readability varied between models: ChatGPT responses were easiest to understand (FRE = 48.5; FKGL = 11.94), while Gemini’s were the most complex (FRE = 29.9; FKGL = 13.3). Conclusions: LLMs show promise in patient-facing communication but currently fall short of providing consistently accurate, complete, and guideline-conform information in high-stakes contexts such as incidental cancer diagnoses. While their tone and structure may support patient engagement, they should not be used autonomously for counseling. Further fine-tuning, clinical validation, and supervision are essential for safe integration into patient care. Full article

Emotion regulation is essential for mental health. However, many people ignore their own emotional regulation or are deterred by the high cost of psychological counseling, which poses significant challenges to making effective support widely available. This review systematically examines the convergence of multimodal sensing technologies and large language models (LLMs) for the development of Automated Emotional Regulation (AER) systems. The review draws upon a comprehensive analysis of the existing literature, encompassing research papers, technical reports, and relevant theoretical frameworks. Key findings indicate that multimodal sensing offers the potential for rich, contextualized data pertaining to emotional states, while LLMs provide improved capabilities for interpreting these inputs and generating nuanced, empathetic, and actionable regulatory responses. The integration of these technologies, including physiological sensors, behavioral tracking, and advanced LLM architectures, presents the improvement of application, moving AER beyond simpler, rule-based systems towards more adaptive, context-aware, and human-like interventions. Opportunities for personalized interventions, real-time support, and novel applications in mental healthcare and other domains are considerable. However, these prospects are counterbalanced by significant challenges and limitations. In summary, this review synthesizes current technological advancements, identifies substantial opportunities for innovation and application, and critically analyzes the multifaceted technical, ethical, and practical challenges inherent in this domain. It also concludes that while the integration of multimodal sensing and LLMs holds significant potential for AER, the field is nascent and requires concerted research efforts to realize its full capacity to enhance human well-being. Full article

This study uses generative AI to investigate the influence of building façade geometry on human physiological and psychological health. Employing Christopher Alexander’s fifteen fundamental properties of living geometry and a set of ten emotional descriptors {beauty, calmness, coherence, comfort, empathy, intimacy, reassurance, relaxation, visual pleasure, well-being} in separate tests, ChatGPT 4.5 evaluates simple, contrasting window designs. AI analyses strongly and consistently prefer traditional window geometries, characterized by symmetrical arrangements and coherent visual structure, over fragmented or minimalist–modernist alternatives. These results suggest human cognitive–emotional responses to architectural forms are hardwired through evolution, privileging specific geometric patterns. Finally, ChatGPT o3 formulates ten detailed geometric rules for empathetic window design and composition. It then applies these criteria to select contemporary window typologies that generate the highest anxiety. The seven most anxiety-inducing designs are the most favored today worldwide. The findings challenge contemporary architectural preferences and standard window archetypes by emphasizing the significance of empathetic and health-promoting façade designs. Given the general suspicion among many readers of the frequently manipulative and unreliable use of AI, its use in this experiment is not to validate design decisions directly, which would put into question what the AI is trained with, but to prove a correlation between two established methodologies for evaluating a design. AI is used as an analytical tool to show that Alexander’s geometric rules (the guidelines proposed beforehand) closely match emotional reactions (the desirable outcomes observed afterward). This novel use of AI suggests integrating neurodesign principles into architectural education and practice to prioritize urban vitality through psychological well-being. Full article

Objectives: Prolonged disorders of consciousness (DoC) present complex diagnostic and therapeutic challenges. This study aimed to evaluate the accuracy of two ChatGPT models (ChatGPT 4o and ChatGPT o1) in answering questions about prolonged DoC, framed as if they were posed by a patient’s relative. Secondary objectives included comparing performance across languages (English vs. Italian) and assessing whether responses conveyed an empathetic tone. Methods: Fifty-seven open-ended questions reflecting common caregiver concerns were generated in both English and Italian, each categorized into one of three domains: clinical data, instrumental diagnostics, or therapy. Each question contained a background context followed by a specific query and was submitted once to both models. Two reviewers evaluated the responses on a four-point scale, ranging from “incorrect and potentially misleading” to “correct and complete”. Discrepancies were resolved by a third reviewer. Accuracy, language differences, empathy, and recommendation to consult a healthcare professional were analyzed using absolute frequencies, percentages, the Mann–Whitney U test, and Chi-squared tests. Results: A total of 228 responses were analyzed. Both models provided predominantly correct answers (80.7–96.8%), with English responses achieving higher accuracy only for ChatGPT 4o on clinical data. ChatGPT 4o exhibited greater empathy in its responses, whereas ChatGPT o1 more frequently recommended consulting a healthcare professional in Italian. Conclusions: Both ChatGPT models demonstrated high accuracy in addressing prolonged DoC queries, highlighting their potential usefulness for caregiver support. However, occasional inaccuracies emphasize the importance of verifying chatbot-generated information with professional medical advice. Full article

Empathetic and coherent responses are critical in automated chatbot-facilitated psychotherapy. This study addresses the challenge of enhancing the emotional and contextual understanding of large language models (LLMs) in psychiatric applications. We introduce Emotion-Aware Embedding Fusion, a novel framework integrating hierarchical fusion and attention mechanisms to prioritize semantic and emotional features in therapy transcripts. Our approach combines multiple emotion lexicons, including NRC Emotion Lexicon, VADER, WordNet, and SentiWordNet, with state-of-the-art LLMs such as Flan-T5, Llama 2, DeepSeek-R1, and ChatGPT 4. Therapy session transcripts, comprising over 2000 samples, are segmented into hierarchical levels (word, sentence, and session) using neural networks, while hierarchical fusion combines these features with pooling techniques to refine emotional representations. Attention mechanisms, including multi-head self-attention and cross-attention, further prioritize emotional and contextual features, enabling the temporal modeling of emotional shifts across sessions. The processed embeddings, computed using BERT, GPT-3, and RoBERTa, are stored in the Facebook AI similarity search vector database, which enables efficient similarity search and clustering across dense vector spaces. Upon user queries, relevant segments are retrieved and provided as context to LLMs, enhancing their ability to generate empathetic and contextually relevant responses. The proposed framework is evaluated across multiple practical use cases to demonstrate real-world applicability, including AI-driven therapy chatbots. The system can be integrated into existing mental health platforms to generate personalized responses based on retrieved therapy session data. The experimental results show that our framework enhances empathy, coherence, informativeness, and fluency, surpassing baseline models while improving LLMs’ emotional intelligence and contextual adaptability for psychotherapy. Full article

This study investigates how interpersonal (speaker–partner) synchrony contributes to empathetic response generation in communication scenarios. To perform this investigation, we propose a model that incorporates multimodal directional (positive and negative) interpersonal synchrony, operationalized using the cosine similarity measure, into empathetic response generation. We evaluate how incorporating specific synchrony affects the generated responses at the language and empathy levels. Based on comparison experiments, models with multimodal synchrony generate responses that are closer to ground truth responses and more diverse than models without synchrony. This demonstrates that these features are successfully integrated into the models. Additionally, we find that positive synchrony is linked to enhanced emotional reactions, reduced exploration, and improved interpretation. Negative synchrony is associated with reduced exploration and increased interpretation. These findings shed light on the connections between multimodal directional interpersonal synchrony and empathy’s emotional and cognitive aspects in artificial intelligence applications. Full article

Objective: This study investigates the perceptions of Long COVID patients in Spain regarding the healthcare they receive to identify demands and areas for improvement. Methods: Using a qualitative descriptive phenomenological approach, the study included 27 participants selected through non-probabilistic convenience sampling. Data were collected via online semi-structured interviews and analyzed using thematic analysis. Results: The findings reveal three key themes: (i) health status and challenges in healthcare during the initial COVID-19 infection; (ii) perceptions about healthcare as Long COVID patients; and (iii) demand for and aspects of improving quality of healthcare. The participants, predominantly women (66.67%) with a median age of 51 years, experienced symptoms that they generally perceived as severe, although only 14.81% required hospitalization. The participants reported initial self-management of symptoms at home, which was influenced by familial responsibilities and hospital overcrowding, and the persistence of a wide range of Long COVID symptoms that significantly impacted their daily lives. Satisfaction with healthcare services varied, with frustrations over systemic inefficiencies and long waiting times. Conclusions: The study highlights the need for timely access to medical care, comprehensive and empathetic healthcare services, and specialized Long COVID units. The results emphasize the importance of patient-centered approaches and multidisciplinary care to address the complex nature of Long COVID effectively. These findings provide crucial insights for improving healthcare protocols and systems to better support Long COVID patients. This study was prospectively registered with the Ethics Committee for Research on Medicines of the Albacete Integrated Health Care Management System (registry) on 22 February 2022 with registration number 2022/001. Full article

This article introduces Alquist 5.0, our SocialBot that was designed for the Alexa Prize SocialBot Grand Challenge 5. Building upon previous iterations, we present the integration of our novel neural response generator (NRG) Barista within a hybrid architecture that combines traditional predefined dialogues with advanced neural response generation. We provide a comprehensive analysis of the current state-of-the-art NRGs and large language models (LLMs), leveraging these insights to enhance Barista’s capabilities. A key focus of our development was in ensuring the safety of our chatbot and implementing robust measures to prevent profanity and inappropriate content. Additionally, we incorporated a new search engine to improve information retrieval and response accuracy. Expanding the capabilities of our system, we designed Alquist 5.0 to accommodate multimodal devices, utilizing APL templates enriched with custom features to deliver an outstanding conversational experience complemented by an excellent user interface. This paper offers detailed insights into the development of Alquist 5.0, which effectively addresses evolving user demands while preserving its empathetic and knowledgeable conversational prowess across a wide range of topics. Full article

Since November 2022, the use of generative artificial intelligence (GAI) technology has increased in many customer service industries. However, little is known about AI’s language choices and meaning-making resources compared to human responses from a systematic linguistic point of view. The present study is a discourse analysis that explores negative online guest complaints made to four luxury heritage hotels in Hong Kong that are classified as cultural heritage sites with rich interpersonal and historical values. We collected authentic guest complaints and responses from hotel managers from April 2012 to October 2022 in online travel forums, and then had GAI draft response letters on behalf of the hotel managers. Our total dataset was 65,539 words and consisted of three subcorpora: guest complaints (Text a of 115 complaints totaling 26,224 words), hotel manager responses (Text b of 115 response letters totaling 14,975 words), and AI-generated responses (Text c of 115 response letters totaling 24,340 words). This study used systemic functional linguistics to explore interpersonal meanings in texts; for example, appraisal resources, verb processes, and personal pronouns were compared between texts. First, we identified the most frequent words of the common themes across the three subcorpora and found significant differences in lexicogrammatical features between hotel managers and AI-generated responses using the log-likelihood ratio. The results suggest that AI-generated texts are able to provide a tailored and empathetic response to guests, but hotel managers may need to introduce some modifications, such as time indicators, sensory verbs used, and complimentary offers. This study explores the differences in word choices and communication strategies, which have implications and insights for the hospitality industry, especially luxury heritage hotels where caring and personalized customer service are considered important. Full article

Migraines are one of the most common and expensive neurological diseases worldwide. Non-pharmacological and digitally delivered treatment options have long been used in the treatment of migraines. For instance, migraine management tools, online migraine diagnosis or digitally networked patients have been used. Recently, applications of ChatGPT are used in fields of healthcare ranging from identifying potential research topics to assisting professionals in clinical diagnosis and helping patients in managing their health. Despite advances in migraine management, only a minority of patients are adequately informed and treated. It is important to provide these patients with information to help them manage the symptoms and their daily activities. The primary aim of this case study was to examine the appropriateness of ChatGPT to handle symptom descriptions responsibly, suggest supplementary assistance from credible sources, provide valuable perspectives on treatment options, and exhibit potential influences on daily life for patients with migraines. Using a deductive, qualitative study, ten interactions with ChatGPT on different migraine types were analyzed through semi-structured interviews. ChatGPT provided relevant information aligned with common scientific patient resources. Responses were generally intelligible and situationally appropriate, providing personalized insights despite occasional discrepancies in interaction. ChatGPT’s empathetic tone and linguistic clarity encouraged user engagement. However, source citations were found to be inconsistent and, in some cases, not comprehensible, which affected the overall comprehensibility of the information. ChatGPT might be promising for patients seeking information on migraine conditions. Its user-specific responses demonstrate potential benefits over static web-based sources. However, reproducibility and accuracy issues highlight the need for digital health literacy. The findings underscore the necessity for continuously evaluating AI systems and their broader societal implications in health communication. Full article

Background/Objectives: ACTION-FRANCE (Awareness, Care, and Treatment In Obesity maNagement in France) aims to identify the perceptions, attitudes, behaviors, and potential barriers to effective obesity management in France and guide collaborative actions. Methods: ACTION-FRANCE is a cross-sectional survey of people with obesity (PwO) and healthcare professionals (HCPs) in France. The PwO and HCP survey questionnaire periods ran from 27 September 2022 to 1 February 2023 and from 19 December 2022 to 31 March 2023, respectively. Results: The study, encompassing 1226 PwO and 166 HCPs, reveals a shared recognition of obesity as a chronic condition. However, despite being requested by most PwO, weight-related discussions are surprisingly infrequent, leading to delayed diagnosis and care. PwO and HCPs held different views as to why: HCPs often attributed it to PwO’s lack of motivation or disinterest, whereas PwO avoided them because they felt weight management was their own responsibility and were uncomfortable discussing it. When weight was discussed, primarily with general practitioners (GPs), discussions mostly focused on physical activity and diet. However, results identified the strong psychosocial impact of obesity: 42% of respondents reported anxiety/depressive symptoms, and many more hesitated to engage in certain social activities because of their weight. Psychotherapy was only discussed by 55% of HCPs. Pharmaceutical options were also rarely discussed (19.5% of HCPs), though 56.1% of PwO reported they would want to. Conclusions: HCPs’ and PwO’s perceptions differed significantly and need to converge through enhanced communication. A holistic approach, integrating comprehensive training for GPs and recognizing psychological comorbidities, would help to bridge perceptual gaps effectively and foster more empathetic and effective patient care. Full article