Empathetic Responses Research Articles

Beyond Automation: A Rigorous Testing Framework for Reliable AI Chatbots in Life Insurance

AI-driven chatbots are transforming customer service in Life Insurance, offering policyholders instant support, streamlined inquiries, and personalized recommendations. However, deploying these chatbots effectively requires addressing unique challenges, including interpreting complex insurance terminology, ensuring regulatory compliance, and maintaining data security and user privacy. This research introduces a detailed testing framework specifically tailored to Life Insurance chatbots, covering functional, non-functional, AI-specific, and compliance testing to guarantee accuracy, reliability, and adherence to legal standards. The framework emphasizes essential practices for verifying natural language understanding, sensitive data handling, and empathetic responses for users navigating critical life events. This research highlights the critical role of targeted testing to deliver robust, user-centered chatbot solutions in the Life Insurance sector.

The psychodynamics of self-harm

SUMMARY This article examines the complex phenomenon of self-harm, exploring its motivations, theoretical underpinnings and the intricate transference and countertransference reactions that arise in clinical settings. It aims to integrate psychiatric understanding with contemporary theories of the impact of trauma on both the body and the mind, to deepen the knowledge of self-harm and increase the effectiveness of treatment approaches. The article argues for a nuanced view of self-harm and emphasises the need for compassionate, well-informed care. By addressing the psychodynamics of self-harm, the article seeks to improve therapeutic outcomes and foster an empathetic and effective clinical response. Fictitious case studies are used to illustrate these concepts, demonstrating the critical role of early attachment experiences and the challenges faced by healthcare providers in management.

The effect of narratives in United Nations Virtual Reality

Viewed as an empathy machine, Virtual Reality (VR) film has been utilized by many humanitarian organizations. to augment individuals’ comprehension of humanitarian issues and evoke empathetic responses. Despite extensive analysis on the impact of virtual reality in eliciting empathy and its narrative techniques, there exists a research gap regarding the specific attributes of UNVR films. This paper critically examines the positive effects, unresolved challenges, and ethical concerns of UNVR films, particularly through the lens of various narrative techniques, including their documentary realism, montage, external authorship, and extra-diegetic voice-over. This paper calls attention to how UNVR films, despite conveying the same content and expressing the same ideas, achieve better effects than one-dimensional or two-dimensional media, enhancing the audience’s comprehensions of suffering groups such as refugees and eliciting empathy, while also pointing out the challenges that UNVR still faces. The paper also analyzes the fundamental deficiencies of UNVR in terms of embodiment and eliciting empathy. It will conclude with suggestions for future research on how to utilize narrative techniques, based on unique features of VR, to enhance the role of UNVR in addressing humanitarian issues.

Factors associated with dementia-related stigma in British adolescents

BackgroundDementia-related stigma is a prominent barrier for people living with dementia, leading to poor well-being and social isolation. Adolescents are an under-researched group in society that may already have experience of dementia and are more susceptible to attitudinal change which makes them ideal targets for anti-stigma initiatives outlined by public health policy. For the development of evidence-based anti-stigma initiatives in adolescents, it is important to understand which socio-demographic groups are most likely to develop stigmatising attitudes and why. This study aims to identify factors of dementia-related stigma in adolescents.MethodsA total of 1,044 adolescents (aged 11–18 years) from across six regions of England were included in the analysis of this cross-sectional, survey-based study. Descriptive statistics and multiple regressions were employed to explore the association between demographic variables, modifiable factors of dementia-related stigma and the outcome of dementia-related stigma. A path analysis via a structural equation model was employed to test for direct and mediatory effects.ResultsMultiple regression models revealed that younger adolescents, those with higher levels of contact with dementia, higher levels of empathy, higher levels of dementia knowledge, and higher affinity to older adults, are associated with more positive dementia attitudes in adolescents (p < 0.05). Within the accepted structural equation model, empathy, level of contact and dementia knowledge were key mediators of dementia-related stigma (p < 0.05).ConclusionThis study highlights that modifiable factors such as level of contact, ageism, and empathy have a potentially important role in how dementia-related stigma may start to form in the adolescent years. Developing contact-based strategies that stimulate empathetic responses may be useful targets for stigma reduction initiatives for adolescents.

CIRG-SL: Commonsense Inductive Relation Graph framework with Soft Labels for Empathetic Response Generation

Empathy, the ability to understand and respond to others’ emotions, is critical in dialogue systems, particularly for applications such as psychological counselling and casual conversation. However, existing approaches often struggle to accurately capture emotional transitions in user utterances and dialogue contexts across multiple levels of granularity. Additionally, the orthogonality of one-hot emotion representations overlooks the subtle relationships between emotion categories. To overcome these limitations, we propose a novel framework: the commonsense inductive relation graph with fine emotional soft labels for empathetic response generation. This framework refines the representation of user utterances by incorporating commonsense knowledge to derive external emotional cues, which are integrated into an adaptive inductive relation graph. This graph explicitly captures and models dynamic emotional trajectories throughout the dialogue. Additionally, we propose a fine-grained soft label construction method that more accurately reflects the nuanced distribution of emotions, replacing the rigid one-hot encoding with a continuous representation that better captures inter-emotion relationships. Our approach achieves strong performance on the benchmark EmpatheticDialogues dataset, with a perplexity score of 27.85, Dist-1 of 1.81, Dist-2 of 6.58, and a dialogue emotion accuracy of 55.65%. These results highlight the effectiveness of our framework in capturing subtle emotions and generating contextually rich, empathetic responses.

Pengaruh Empathy Response, Anonymity, dan Customization terhadap Customer Trust pada Chatbot Customer Service Tokopedia

Artificial intelligence (AI) technology has grown rapidly in customer service, including AI chatbots. Tokopedia has adopted an AI chatbot for customer service, but there are still many users who do not trust it because it lacks reliability. This study aims to examine the effect of AI chatbot dimensions on customer trust in Tokopedia, focusing on the variables of empathy response, anonymity, customization, and interaction. This research is quantitative using descriptive and causal methods, involving 437 Tokopedia user respondents through structured questionnaires. Data analysis using the SEM-PLS model with SmartPLS. The results show that empathy response, anonymity, customization, and interaction have a positive and significant influence on customer trust. In addition, empathy response, anonymity, and customization also have a positive effect on interaction. The suggestion for Tokopedia is to improve the quality of chatbots in providing empathetic responses, such as greeting users, appreciating, and validating their problems. Innovation in the aspects of empathy response, anonymity, customization, and interaction is also important. Future research could explore additional factors that influence customer trust as well as the mediating or moderating effects of certain variables.

Efektivitas Penghapusan Denda Administrasi Piutang Pajak Bumi dan Bangunan di Kota Bandung

Artificial intelligence (AI) technology has grown rapidly in customer service, including AI chatbots. Tokopedia has adopted an AI chatbot for customer service, but there are still many users who do not trust it because it lacks reliability. This study aims to examine the effect of AI chatbot dimensions on customer trust in Tokopedia, focusing on the variables of empathy response, anonymity, customization, and interaction. This research is quantitative using descriptive and causal methods, involving 437 Tokopedia user respondents through structured questionnaires. Data analysis using the SEM-PLS model with SmartPLS. The results show that empathy response, anonymity, customization, and interaction have a positive and significant influence on customer trust. In addition, empathy response, anonymity, and customization also have a positive effect on interaction. The suggestion for Tokopedia is to improve the quality of chatbots in providing empathetic responses, such as greeting users, appreciating, and validating their problems. Innovation in the aspects of empathy response, anonymity, customization, and interaction is also important. Future research could explore additional factors that influence customer trust as well as the mediating or moderating effects of certain variables.

Feeling, thinking, acting

Abstract This article considers the multi- and intersemiotic expression of empathy and compassion in a campaign organised by the Vegan Society. It draws upon insights from ecofeminism and the ethics of care as well as systemic functional semiotics as a way of exploring how instances of attitude (affect, judgment and appreciation) in the campaign’s various texts might be negotiated and shared, creating potentials for empathetic and compassionate responses. The study finds that parts of the campaign represent empathy and compassion as exemplars for readers to follow, while other parts of the campaign, especially social media, provide readers with an opportunity to enact empathy and compassion. The study also identifies gendered and generational dimensions, and suggests that syndromes or clusters of positive and negative attitude can form the basis for empathetic and compassionate responses.

Is it possible for people to develop a sense of empathy toward humanoid robots and establish meaningful relationships with them?

Empathy can be described as the ability to adopt another person's perspective and comprehend, feel, share, and respond to their emotional experiences. Empathy plays an important role in these relationships and is constructed in human-robot interaction (HRI). This systematic review focuses on studies investigating human empathy toward robots. We intend to define empathy as the cognitive capacity of humans to perceive robots as equipped with emotional and psychological states. We conducted a systematic search of peer-reviewed articles using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. We searched Scopus, PubMed, Web of Science, and Embase databases. All articles were reviewed based on the titles, abstracts, and full texts by two investigators (EM and CS) who independently performed data collection. The researchers read the full-text articles deemed suitable for the study, and in cases of disagreement regarding the inclusion and exclusion criteria, the final decision was made by a third researcher (VLB). The electronic search identified 484 articles. After reading the full texts of the selected publications and applying the predefined inclusion criteria, we selected 11 articles that met our inclusion criteria. Robots that could identify and respond appropriately to the emotional states of humans seemed to evoke empathy. In addition, empathy tended to grow more when the robots exhibited anthropomorphic traits. Humanoid robots can be programmed to understand and react to human emotions and simulate empathetic responses; however, they are not endowed with the same innate capacity for empathy as humans.

Performance of Large Language Models in Patient Complaint Resolution: Web-Based Cross-Sectional Survey.

Patient complaints are a perennial challenge faced by health care institutions globally, requiring extensive time and effort from health care workers. Despite these efforts, patient dissatisfaction remains high. Recent studies on the use of large language models (LLMs) such as the GPT models developed by OpenAI in the health care sector have shown great promise, with the ability to provide more detailed and empathetic responses as compared to physicians. LLMs could potentially be used in responding to patient complaints to improve patient satisfaction and complaint response time. This study aims to evaluate the performance of LLMs in addressing patient complaints received by a tertiary health care institution, with the goal of enhancing patient satisfaction. Anonymized patient complaint emails and associated responses from the patient relations department were obtained. ChatGPT-4.0 (OpenAI, Inc) was provided with the same complaint email and tasked to generate a response. The complaints and the respective responses were uploaded onto a web-based questionnaire. Respondents were asked to rate both responses on a 10-point Likert scale for 4 items: appropriateness, completeness, empathy, and satisfaction. Participants were also asked to choose a preferred response at the end of each scenario. There was a total of 188 respondents, of which 115 (61.2%) were health care workers. A majority of the respondents, including both health care and non-health care workers, preferred replies from ChatGPT (n=164, 87.2% to n=183, 97.3%). GPT-4.0 responses were rated higher in all 4 assessed items with all median scores of 8 (IQR 7-9) compared to human responses (appropriateness 5, IQR 3-7; empathy 4, IQR 3-6; quality 5, IQR 3-6; satisfaction 5, IQR 3-6; P<.001) and had higher average word counts as compared to human responses (238 vs 76 words). Regression analyses showed that a higher word count was a statistically significant predictor of higher score in all 4 items, with every 1-word increment resulting in an increase in scores of between 0.015 and 0.019 (all P<.001). However, on subgroup analysis by authorship, this only held true for responses written by patient relations department staff and not those generated by ChatGPT which received consistently high scores irrespective of response length. This study provides significant evidence supporting the effectiveness of LLMs in resolution of patient complaints. ChatGPT demonstrated superiority in terms of response appropriateness, empathy, quality, and overall satisfaction when compared against actual human responses to patient complaints. Future research can be done to measure the degree of improvement that artificial intelligence generated responses can bring in terms of time savings, cost-effectiveness, patient satisfaction, and stress reduction for the health care system.

Strengthening student empathy in GeoCapabilities: Digital learning innovations and pedagogical strategies for disaster mitigation

Indonesia’s geographical positioning along the ‘Ring of Fire’ exposes it to frequent seismic activities, making effective disaster mitigation education crucial. Current educational strategies may not adequately foster the necessary empathy and understanding among students regarding the socio-environmental impacts of disasters. This study aims to develop and evaluate a digital learning platform designed to enhance GeoCapabilities in students, particularly focusing on the social-environmental empathy dimension. The objective is to improve students’ empathetic responses to disaster scenarios through integrated disaster mitigation pedagogy. Utilizing the design-based research method, this research involved a systematic blend of iterative development and evaluation phases to refine educational interventions. Data collection was achieved through a combination of qualitative feedback from students and quantitative pre-and post-test measures to assess empathy levels. Data analysis involved statistical testing to determine the effectiveness of the digital learning platform in enhancing empathetic capabilities among learners. The research reveals that the digital learning platform (D-Learning), significantly improves students’ empathy towards disaster impacts. Students demonstrated a deeper understanding and emotional engagement with the content, highlighting an increase in their ability to empathize with affected communities. The findings suggest that the scalability of D-Learning can be tailored to different regions, providing a valuable tool for enhancing disaster preparedness worldwide. The integration of technology and empathy-focused pedagogy in disaster education could serve as a model for developing similar educational programs globally, aiming to foster a more resilient and empathetic future generation.

Role of ChatGPT in antenatal care

ChatGPT, developed by OpenAI, represents a significant advancement in AI technology, particularly noted for its ability to engage in human-like conversations. This review article is about role of ChatGPT in antenatal care during pregnancy and its limitations in addressing health-related issues. While ChatGPT offers accessible and empathetic responses to queries about pregnancy and childbirth, its reliability and accuracy remain concerns. The model's reliance on statistical patterns in data often leads to biased or incomplete information, lacking necessary citations. Despite these limitations, ChatGPT shows promise in supporting clinical decision-making but requires oversight to ensure medical advice is precise and appropriate. Ethical considerations, including privacy and misuse risks, underscore the need for further development and validation in healthcare applications.

EmpCI: Empathetic response generation with common sense and empathetic intent

Empathy plays an important role in human conversations as an ability that enables individuals to understand the emotions and situations of others. Integrating empathy into dialogue systems is a crucial step in making them humanized. Relevant psychological studies have shown that a complete, high-quality empathetic dialogue should consist of the following two stages: (1) Empathetic Perception: the listener needs to perceive the emotional state of the speaker from both cognitive and affective aspects; (2) Empathetic Expression: the appropriate expression is chosen to respond to the perceived information. However, many existing studies on empathetic response generation only focus on one of these stages, resulting in incomplete and insufficiently empathetic responses. To this end, we propose the EmpCI, a two-stage empathetic response generation model that utilizes commonsense knowledge and mixed empathetic intent, respectively. Specifically, we use commonsense knowledge in the first stage to enhance the model’s perception of the user’s emotion and introduce mixed empathetic intent in the second stage to generate responses with appropriate expressions for the perceived information. Finally, we evaluated the EmpCI on the EmpatheticDialogues dataset, and extensive experiment results show that the proposed model outperforms the baselines in both perceiving users’ emotions and generating empathetic responses.

Beware of Strangers: Dogs' Empathetic Response to Unknown Humans.

Empathy is a complex cognitive ability that has been studied in many social animals, including dogs. Previous studies have found that dogs would rescue their distressed owner more quickly than a calm owner and that dogs respond physiologically and behaviorally to the sound of crying strangers. However, no studies have explored the empathetic and emotional contagion capabilities of dogs towards strangers in rescue paradigms. In the present study, a stranger was placed behind a clear door and was told to cry (distress) or hum (neutral). The dogs' door opening, stress behaviors, tone of approach, and physiological responses were measured. Dogs did not open more frequently or more quickly for the stranger in the distressed condition compared to the neutral condition. Additionally, there was no significant difference between the behavioral or physiological indicators of stress across conditions. It was also found that non-openers were reported by owners to have more fear and, in the empathy test, were more aggressive and fearful in their tone of approach. These results suggest that dogs may be less likely to exhibit empathy-like behaviors to unknown humans in an unfamiliar environment and that owners may be necessary to moderate a dog's stress to show empathetic behaviors.

Empathy's Crucial Role: Unraveling Impact on Students Bullying Behavior - A Scoping Review.

Bullying behavior among students is a serious problem in the educational context and has an impact on victims and perpetrators. Bullying has serious impacts, both emotionally and psychologically, especially for victims who are vulnerable to stress, depression, and even in extreme cases, can lead to suicidal tendencies. Empathy is a key factor in responding to bullying situations. So empathy is an important aspect in reducing bullying behavior. The aim of this research is to explore the role of empathy in bullying behavior in students. The scoping review method was used in this research. The keywords used are empathy, bullying, and students. Search for articles in three databases, namely CINAHL, PubMed, and Scopus. The inclusion criteria in the article search were samples are students (elementary schools students until high schools students) English language, discussion of empathy, publication of articles in the last 10 years (2014-2023), and original research. Grey literature excluded in this scoping review. Data analysis using thematic analysis. The authors found 13 articles that discussed the influence of empathy on bullying behavior in students. Findings from the articles analyzed highlight the complexity of the interactions between affective and cognitive empathy and students behavior in the context of bullying. Students with high levels of empathy tend to be more active in defending victims of bullying, while low levels of empathy tend to reinforce bullying behavior or passive bystander attitudes. Intervention programs that include social and emotional skills training, awareness campaigns, and learning approaches that promote tolerance and respect for diversity can have the potential to reduce the incidence of bullying in students. Increasing understanding and empathetic responses can be an effective strategy in addressing bullying problems in schools and communities.

Improving Spiritual Well-Being of Polish Pain Outpatients: A Feasibility Mixed Methods Study.

Introduction: A physician in a chronic pain treatment clinic must recognize that the relationship between pain and spirituality is bidirectional. Chronic pain can decrease the level of spiritual well-being, and low spiritual well-being can also significantly intensify the perception of pain and worsen coping with it. Currently, for many scientific and medical communities, it is evident that spiritual care is an indispensable element of holistic medicine. Objective: The authors developed a non-religious spiritual care model provided by a physician at a chronic pain treatment clinic from May 2022 to February 2024. Method: The study utilized a mixed-method approach to conduct the research. The analysis consisted of twelve patients. A FACIT-Sp-12 questionnaire evaluated the individual's spiritual well-being before the intervention. The intervention involved asking patients open-ended questions about their life history, experiences, and spiritual beliefs and the physician's use of active listening and empathetic responses to what patients shared (relationship-building activities). The intervention aimed to assist patients in accepting the limitations of an incurable chronic disease, affirming the value of their lives, enhancing inner harmony, and increasing their sense of belonging to something greater. After the intervention, a re-assessment of the patient's spiritual well-being was conducted using the FACIT-Sp-12 questionnaire. Researchers collected qualitative data through a confidential survey that included the following instructions: "Please express an anonymous opinion on how you perceive the spiritual care provided by the physician". Results: There was an increase in spiritual well-being, assessed using the FACIT-Sp-12 scale, in 9 out of 12 patients. The median, as well as the average, level of spiritual well-being increased in a statistically significant way after the intervention (p < 0.05). This was primarily due to the higher value of the peace subscale of the questionnaire. Qualitative analysis revealed benefits reported by patients (personal development, gratitude, satisfaction, support, hope) resulting from physician's actions. Conclusions: Both qualitative and quantitative data showed that establishing a relationship with the doctor improves the spiritual well-being of patients. Therefore, this model can be recommended for physicians in chronic pain treatment clinics.

Integrating discourse features and response assessment for advancing empathetic dialogue

Empathetic response generation is a crucial task in natural language processing, enabling emotionally resonant machine–human interactions. In this paper, we introduce the InfRa (Integrating Discourse Features and Response Assessment) model to address limitations in traditional methods for this task, such as the lack of deep dialogue comprehension and response control. InfRa integrates discourse features to augment structural dialogue understanding, with a novel edge pruning and mutual information learning module to further refine the representation. The model also employs a response evaluation module for dynamic optimization, ensuring emotional and semantic consistency between the generated response and its context. Our experiments demonstrate that InfRa outperforms existing baselines, reducing the Perplexity (PPL) score by approximately 9 points and excelling in all three fine-grained aspects of human evaluation. This research not only advances the development of empathetic chatbots but also provides valuable insights for broader text generation tasks.

The effect of empathetic response and consumers’ narcissism in voice-based artificial intelligence

Voice-based artificial intelligence, or voice AI, is becoming more prevalent in consumers' daily transactions. Utilizing the perception-action model of empathy, this study aims to understand the holistic nature of empathetic responses in voice AI and how this technology, when rendered empathetic, can affect consumers' attention to auditory information (perceived attention) and auditory information exploration, by reaching expected outcomes of the interactive process, consumer satisfaction, and consumers' willingness to use voice AI. The results of two pretests and two experiments explain the effect of empathetic response in voice AI on consumers' perceived attention and its subsequent effect on consumers' auditory information exploration, satisfaction, and willingness to use voice AI. In addition, the moderating effects of narcissism on relationships were also tested. Consumers’ narcissism strengthens the effect of empathetic response on perceived attention to auditory information.

Spanish MEACorpus 2023: A multimodal speech–text corpus for emotion analysis in Spanish from natural environments

In human–computer interaction, emotion recognition provides a deeper understanding of the user’s emotions, enabling empathetic and effective responses based on the user’s emotional state. While deep learning models have improved emotion recognition solutions, it is still an active area of research. One important limitation is that most emotion recognition systems use only text as input, ignoring features such as voice intonation. Another limitation is the limited number of datasets available for multimodal emotion recognition. In addition, most published datasets contain emotions that are simulated by professionals and produce limited results in real-world scenarios. In other languages, such as Spanish, hardly any datasets are available. Therefore, our contributions to emotion recognition are as follows. First, we compile and annotate a new corpus for multimodal emotion recognition in Spanish (Spanish MEACorpus 2023), which contains 13.16 h of speech divided into 5129 segments labeled by considering Ekman’s six basic emotions. The dataset is extracted from YouTube videos in natural environments. Second, we explore several deep learning models for emotion recognition using text- and audio-based features. Third, we evaluate different multimodal techniques to build a multimodal recognition system that improves the results of unimodal models, achieving a Macro F1-score of 87.745%, using late fusion with concatenation strategy approach.

Neuroarchitecture: How the Perception of Our Surroundings Impacts the Brain.

The study of neuroarchitecture is concerned with the significant effects of architecture on human behavior, emotions and thought processes. This review explores the intricate relationship between the brain and perceived environments, focusing on the roles of the anterior cingulate cortex (ACC) and parahippocampal place area (PPA) in processing architectural stimuli. It highlights the importance of mirror neurons in generating empathetic responses to our surroundings and discusses how architectural elements like lighting, color, and space layout significantly impact emotional and cognitive experiences. The review also presents insights into the concept of cognitive maps and spatial navigation, emphasizing the role of architecture in facilitating wayfinding and orientation. Additionally, it addresses how neuroarchitecture can be applied to enhance learning and healing environments, drawing upon principles from the Reggio Emilia approach and considerations for designing spaces for the elderly and those with cognitive impairments. Overall, this review offers a neuroscientific basis for understanding how human cognition, emotions, spatial navigation, and well-being are influenced by architectural design.