Pedagogical sentiment analysis based on the BERT-CNN-BiGRU-attention model in the context of intercultural communication barriers.

Amid the wave of globalization, the phenomenon of cultural amalgamation has surged in frequency, bringing to the fore the heightened prominence of challenges inherent in cross-cultural communication. To address these challenges, contemporary research has shifted its focus to human-computer dialogue. Especially in the educational paradigm of human-computer dialogue, analysing emotion recognition in user dialogues is particularly important. Accurately identify and understand users' emotional tendencies and the efficiency and experience of human-computer interaction and play. This study aims to improve the capability of language emotion recognition in human-computer dialogue. It proposes a hybrid model (BCBA) based on bidirectional encoder representations from transformers (BERT), convolutional neural networks (CNN), bidirectional gated recurrent units (BiGRU), and the attention mechanism. This model leverages the BERT model to extract semantic and syntactic features from the text. Simultaneously, it integrates CNN and BiGRU networks to delve deeper into textual features, enhancing the model's proficiency in nuanced sentiment recognition. Furthermore, by introducing the attention mechanism, the model can assign different weights to words based on their emotional tendencies. This enables it to prioritize words with discernible emotional inclinations for more precise sentiment analysis. The BCBA model has achieved remarkable results in emotion recognition and classification tasks through experimental validation on two datasets. The model has significantly improved both accuracy and F1 scores, with an average accuracy of 0.84 and an average F1 score of 0.8. The confusion matrix analysis reveals a minimal classification error rate for this model. Additionally, as the number of iterations increases, the model's recall rate stabilizes at approximately 0.7. This accomplishment demonstrates the model's robust capabilities in semantic understanding and sentiment analysis and showcases its advantages in handling emotional characteristics in language expressions within a cross-cultural context. The BCBA model proposed in this study provides effective technical support for emotion recognition in human-computer dialogue, which is of great significance for building more intelligent and user-friendly human-computer interaction systems. In the future, we will continue to optimize the model's structure, improve its capability in handling complex emotions and cross-lingual emotion recognition, and explore applying the model to more practical scenarios to further promote the development and application of human-computer dialogue technology.

A Dialogue about Vaccine Side Effects: Understanding Difficult Pandemic Experiences.

This paper investigates the relationship between the experiences of mass vaccinations against two pandemic viruses: the swine flu in 2009-2010 and COVID-19 in the early 2020s. We show how distressing memories from the swine flu vaccination, which led to the rare but severe adverse effect of narcolepsy in approximately 500 children in Sweden, were triggered by the COVID-19 pandemic. The narcolepsy illness story has rarely been told in academic contexts; therefore, we will provide space for this story. It is presented through a dialogue with the aim of shedding light on the interrelationship between pandemics-and between mass vaccinations-to investigate what could be termed cultural wounds that influence societies because they are characterized by the difficulty of talking about them. The paper explores the multiple shocks of illness in life and what can be learned from them by sharing them.

The development and initial evaluation of conversation cards for optimizing consultations for patients with atopic dermatitis.

Purpose: Patients with atopic dermatitis (AD) require both skills and support to effectively manage life with the disease. Here, we developed an agenda-setting tool for consultations with patients with AD to establish a collaborative agenda that enhances patient involvement and prioritizes on self-management support.Materials and methods: Using the design thinking process, we included 64 end-users (patients and healthcare professionals (HCPs)) across the different phases of design thinking. We identified seven overall categories that patients find important to discuss during consultations, which informed the development of a tool for co-creating a consultation agenda (conversation cards, CCs).Results: Through iterative user testing of the CCs, patients perceived the cards as both inspiring and an invitation from HCPs to openly discuss their needs during consultations. Healthcare professionals have found the CCs easy to use, despite the disruption to the typical consultation process.Conclusion: In summary, the CCs provide a first-of-its-kind agenda-setting tool for patients with AD. They offer a simple and practical method to establishing a shared agenda that focuses on the patients' needs and are applicable within real-world clinical settings.

Translating motivational interviewing for the HPV vaccine into a computable ontology model for automated AI conversational interaction.

Human papillomavirus (HPV) vaccinations are lower than expected. To protect the onset of head and neck cancers, innovative strategies to improve the rates are needed. Artificial intelligence may offer some solutions, specifically conversational agents to perform counseling methods. We present our efforts in developing a dialogue model for automating motivational interviewing (MI) to encourage HPV vaccination. We developed a formalized dialogue model for MI using an existing ontology-based framework to manifest a computable representation using OWL2. New utterance classifications were identified along with the ontology that encodes the dialogue model. Our work is available on GitHub under the GPL v.3. We discuss how an ontology-based model of MI can help standardize/formalize MI counseling for HPV vaccine uptake. Our future steps will involve assessing MI fidelity of the ontology model, operationalization, and testing the dialogue model in a simulation with live participants.

Recommendations for designing conversational companion robots with older adults through foundation models.

Companion robots are aimed to mitigate loneliness and social isolation among older adults by providing social and emotional support in their everyday lives. However, older adults' expectations of conversational companionship might substantially differ from what current technologies can achieve, as well as from other age groups like young adults. Thus, it is crucial to involve older adults in the development of conversational companion robots to ensure that these devices align with their unique expectations and experiences. The recent advancement in foundation models, such as large language models, has taken a significant stride toward fulfilling those expectations, in contrast to the prior literature that relied on humans controlling robots (i.e., Wizard of Oz) or limited rule-based architectures that are not feasible to apply in the daily lives of older adults. Consequently, we conducted a participatory design (co-design) study with 28 older adults, demonstrating a companion robot using a large language model (LLM), and design scenarios that represent situations from everyday life. The thematic analysis of the discussions around these scenarios shows that older adults expect a conversational companion robot to engage in conversation actively in isolation and passively in social settings, remember previous conversations and personalize, protect privacy and provide control over learned data, give information and daily reminders, foster social skills and connections, and express empathy and emotions. Based on these findings, this article provides actionable recommendations for designing conversational companion robots for older adults with foundation models, such as LLMs and vision-language models, which can also be applied to conversational robots in other domains.

Enhancing cervical cancer knowledge among women of reproductive age: a dialogue-based community health education intervention in rural Kisumu County, Kenya.

BACKGROUND: Cervical cancer is a leading cause of cancer death among women of reproductive age despite being treatable if it is diagnosed early. Early diagnosis is possible through regular screening through the public health system. However, screening rates remain low in many low- and middle-income countries, including Kenya, where the screening rate currently stands at 16-18%. The low screening rates are attributed to, among other factors, low knowledge about cervical cancer and the available screening options among women of reproductive age. The current study evaluated the effectiveness of dialogue-based community health education by trained community health volunteers (CHVs) in improving cervical cancer knowledge among women of reproductive age (WRA) in rural Kisumu County. METHODS: This was a longitudinal pre- and post-intervention study with a control group. The knowledge of women of reproductive age was assessed at baseline in both the intervention and control groups, followed by dialogue-based community health education in the intervention arm. A final end-line knowledge assessment was performed. The scores at baseline and at the end of the study were compared to assess changes in knowledge due to the intervention. The proportion of WRA with improved knowledge was also calculated, and statistical significance was considered at p ≤ 0.05. RESULTS: There was no significant difference between the participants in the two arms, except for the level of education (p = 0.002). The knowledge of the WRA in the intervention arm improved significantly (p < 0.001) following the dialogue-based educational intervention by the trained CHVs. None of the demographic characteristics were associated with knowledge. CONCLUSION: Dialogue-based educational intervention significantly improved the knowledge of the WRA in the intervention arm, showing its potential to address the knowledge gap in the community.

Would you be impressed: applying principles of magic to chatbot conversations.

A magician's trick and a chatbot conversation have something in common: most of their audiences do not know how they work. Both are also constrained by their own limitations: magicians by the constraints of biology and physics, and dialogue systems by the status of current technology. Magicians and chatbot creators also share a goal: they want to engage their audience. But magicians, unlike the designers of dialogue systems, have centuries of practice in gracefully skirting limitations in order to engage their audience and enhance a sense of awe. In this paper, we look at these practices and identify several key principles of magic and psychology to apply to conversations between chatbots and humans. We formulate a model of communication centered on controlling the user's attention, expectations, decisions, and memory based on examples from the history of magic. We apply these magic principles to real-world conversations between humans and a social robot and evaluate their effectiveness in a Magical conversation setting compared to a Control conversation that does not incorporate magic principles. We find that human evaluators preferred interactions that incorporated magical principles over interactions that did not. In particular, magical interactions increased 1) the personalization of experience, 2) user engagement, and 3) character likability. Firstly, the magical experience was "personalized." According to survey results, the magical conversation demonstrated a statistically significant increase in "emotional connection" and "robot familiarity." Therefore, the personalization of the experience leads to higher levels of perceived impressiveness and emotional connection. Secondly, in the Magical conversation, we find that the human interlocutor is perceived to have statistically-significantly higher engagement levels in four of seven characteristics. Thirdly, participants judged the robot in the magical conversation to have a significantly greater degree of "energeticness,""humorousness," and "interestingness." Finally, evaluation of the conversations with questions intended to measure contribution of the magical principals showed statistically-significant differences for five out of nine principles, indicating a positive contribution of the magical principles to the perceived conversation experience. Overall, our evaluation demonstrates that the psychological principles underlying a magician's showmanship can be applied to the design of conversational systems to achieve more personalized, engaging, and fun interactions.

Enhancing the delivery of comprehensive care for people living with HIV in Canada: insights from citizen panels and a national stakeholder dialogue.

BACKGROUND: People living with human immunodeficiency virus (HIV) are living longer with health-related disability associated with ageing, including complex conditions. However, health systems in Canada have not adapted to meet these comprehensive care needs. METHODS: We convened three citizen panels and a national stakeholder dialogue. The panels were informed by a plain-language citizen brief that outlined data and evidence about the challenge/problem, elements of an approach for addressing it and implementation considerations. The national dialogue was informed by a more detailed version of the same brief that included a thematic analysis of the findings from the panels. RESULTS: The 31 citizen panel participants emphasized the need for more prevention, testing and social supports, increased public education to address stigma and access to more timely data to inform system changes. The 21 system leaders emphasized the need to enhance person-centred care and for implementing learning and improvement across provinces, territories and Indigenous communities. Citizens and system leaders highlighted that policy actions need to acknowledge that HIV remains unique among conditions faced by Canadians. CONCLUSIONS: Action will require a national learning collaborative to support spread and scale of successful prevention, care and support initiatives. Such a collaborative should be grounded in a rapid-learning and improvement approach that is anchored on the needs, perspectives and aspirations of people living with HIV; driven by timely data and evidence; supported by appropriate decision supports and aligned governance, financial and delivery arrangements; and enabled with a culture of and competencies for rapid learning and improvement.

Identity development in multicultural context: Multidimensional self exploration approaches employed by Modern Orthodox women.

The aim of this study is to examine identity development of Modern Orthodox women as they pursue their studies within a multicultural and multi-faith environment. Content analysis was used to analyze the final papers of undergraduate religious female students in Israel (N = 47) who participated in a semester-long dialogue course for Jewish students. The findings revealed three salient themes, suggesting that women's self-exploration developed noticeably within a rich multicultural context: (a) participants engaged in self-reflection by drawing comparisons between themselves and Arab students, leading to an exploration of their religious beliefs and group affiliations; (b) participants embraced their individuality within a multicultural context while balancing their religious duties; and (c) participants critically examined the status of Orthodox women in society, particularly within the family context. These findings highlight the process of identity exploration among Modern Orthodox women, complicated by intersections of religion, gender, and culture. In doing so, this study contributes to the understanding of identity development in multicultural societies.

'Atawhai': a primary care provider-led response to family violence in Aotearoa New Zealand.

BACKGROUND: As a key determinant of ill-health, family violence is inadequately responded to within Aotearoa New Zealand health policy and practice. Without adequate system support, health professionals can often be unsure of what to do, or how to help. Developed in response to this system gap, 'Atawhai' aims to make it easier for primary care professionals to respond to family violence. METHODS: Underpinned by indigenous Maori customs, Atawhai combines complexity theory and participatory research methodologies to be responsive to the complexity involved in family violence. We worked with 14 primary care professionals across ten whakawhitiwhiti korero wananga (meetings for deliberate dialogue) to identify and develop primary care system pathways and tools for responding to family violence. This paper focuses on the development of Atawhai through wananga and observation methods. Methods used to capture change will be reported separately. FINDINGS: Atawhai is a relational response to family violence, focused on developing a network of trusted relationships between health and social care professionals to support safe responses to those accessing care. This study identified four key health system pathways to responsiveness and developed associated tools to support health care responsiveness to family violence. We found the quality of relationships, both among professionals and with those accessing care, coupled with critical reflection on the systems and structures that shape policy and practice are essential in generating change within primary care settings. CONCLUSIONS: Atawhai is a unique health care response to family violence evidenced on empirical knowledge of primary care professionals. Our theoretical lens calls attention to parts of the system often obscured by current health care responses to family violence. Atawhai presents an opportunity to develop a grassroots-informed, long-term response to family violence that evolves in response to needs.

Dialogue of knowledge in traditional herbal medicine in Mé'pháá and Tu'un savi indigenous peoples in the mountain of Guerrero Mexico / Diálogo de saberes en la medicina tradicional herbolaria en pueblos indígenas Mé'pháá y Tu'un savi en la Montaña de Guerrero, México

In the indigenous peoples Tu'un savi and Mé'pháá of the mountain region of guerrero, allopathic medicine and traditional herbal medicine are used, due to this, we consider that dialogues of knowledge should be established between the practitioners of both medicines. We collaborated with 46 individuals to discuss the forms of using medicinal species, preparing treatments, and using allopathic medicine. Through semi-structured and in-depthinterviews, 121 plant species were recorded, with which more than 40 diseases are treated, which are distributed in the digestive, muscular, respiratory, and urinary systems:chronic-degenerative and cultural diseases. The dialogue of knowledge between specialists in traditional medicine and allopathic doctors could contribute to the development of their own health project, with which a regional ethnodevelopment plan could be created.

En los pueblos indígenas Tu'un savi y Mé'pháá de la montaña de Guerrero se utiliza la medicina alopática y la medicina tradicional herbolaria, debido a ello, consideramos que deberían establecerse diálogos de saberes entre los practicantes de ambas medicinas. Se trabajó con 46 colaboradores, con los cuales se dialogó acerca de las formas de uso de las especies medicinales, preparación de los tratamientos y utilización de l a medicina alopática. A través de entrevistas semiestructuradas y a profundidad se registraron 121 especies de plantas, con las que se tratan más de 40 enfermedades, las cuales están distribuidas en los sistemas digestivo, respiratorio y urinario; también se atienden enfermedades crónico - degenerativas y culturales. El diálogo de saberes entre especialistas de la medicina tradicional y médicos alópatas podría contribuir a la elaboración de un proyecto de salud propio, con el cual se podría crear un plan de e tnodesarrollo regional

Treating Guilt-Inducing Self-Talk in Ocd with Dramatized Socratic Dialogue: A Step by Step Intervention.

Objective: Fear of moral guilt and conseque:nt increased attention to personal actions and intentions are the main ingredients of the self-criticism in patients suffering from obsessive-compulsive disorder (OCD). This pathogenic attitude takes shape in a typical guilt-inducing self-talk.The purpose of this work is to describe in detail a novel cognitive therapeutic procedure for OCD called "Dramatized Socratic Dialogue" (DSD). Method: DSD is a theory-oriented intervention that combine elements of Socratic dialogue, chairwork, and cognitive acceptance strategies derived from Mancini's model, which posits that obsessive-compulsive (OC) symptoms stem from a fear of deontological guilt. Results: DSD appears to have many strengths, being a theory-oriented treatment and focusing, as a therapeutic target, on the cognitive structures that determine pathogenic processes and OC symptoms. Furthermore, it is a short, flexible and tailor-made intervention. Conclusions: Detailed description of the intervention could foster future research perspectives and thus be used in evidence-based effectiveness studies to establish whether DSD reduces OC symptoms and to investigate its mechanism of action.

Grappling With the Inclusion of Patients and the Public in Consensus Building: A Commentary on Inclusion, Safety, and Accessibility; Comment on "Evaluating Public Participation in a Deliberative Dialogue: A Single Case Study".

Deliberative dialogue (DD) may be relatively new in health research but has a rich history in fostering public engagement in political issues. Dialogic approaches are future-facing, comprising structured discussions and consensus building activities geared to the collective identification of actionable and contextualized solutions. Relying heavily on a need for coproduction and shared leadership, these approaches seek to garner meaningful collaborations between researchers and knowledge users, such as healthcare providers, decision-makers, patients, and the public. In this commentary, we explore some of the challenges, successes, and opportunities arising from public engagement in DD, drawing also upon insights gleaned from our own research, along with the case study presented by Scurr and colleagues. Specifically, we seek to expand discussions related to inclusion, power, and accessibility in DD, highlight the need for scholarship that addresses the epistemic, methodological, and practical aspects of patient and public engagement within dialogic methods, and identify promising practices.

Power, position and social relations: Is the espoused absence of hierarchy in Open Dialogue naïve?

Open Dialogue practitioners aim to reduce social hierarchies by not privileging any one voice in social network conversations, and thus creating space for a polyphony of voices. This sits in contrast to the traditional privileging of those voices credited with more knowledge or power because of social position or professional expertise. Using qualitative interviews, the aim of this current study was to explore Open Dialogue practitioners' descriptions of challenges in implementing Open Dialogue at a women's health clinic in Australia. Findings revealed how attempts to rhetorically flatten hierarchies among practitioners created challenges and a lack of clarity regarding roles and responsibilities. As the practitioners tried to adjust to new ways of working, they reverted to taking up engrained positions and power aligned with more conventional social and professional roles for leading therapy and decision-making. The findings raise questions about equity-oriented ways of working, such as Open Dialogue, where intentions of creating a flattened hierarchy may allow power structures and their effects to be minimised or ignored, rather than actively acknowledged and addressed. Further research is needed to consider the implications that shifting power relations might have on the roles and responsibilities of practitioners in the move to equity-oriented services.

Electroencephalography (EEG) Evidence for the Psychological Processes of Humor Generation: A Comparison Perspective on Humor and Creativity.

(1) Background: Humor stands out as the most dynamic and innovative aspect of human intelligence. Drawing on the cognitive parallels between humor and creativity, this study explored the EEG alpha frequency band activity patterns during humor generation by comparing the process of generating humorous and creative ideas. (2) Methods: Thirty-six participants were randomly assigned to either the humor generation group or the creative generation group, and the dependent variable was the neural oscillation in both low-frequency and high-frequency alpha during the early, middle, and late stages of both humor and creative generation. (3) Results: In the early stages, both humor and creative generation exhibited significantly higher power in low-frequency alpha and high-frequency alpha in the temporal region compared to the middle and late stages. In the middle and late stages, the low-frequency alpha oscillation in the frontal region for humor generation was significantly higher than that for creative generation. (4) Conclusions: Humor and creative generation share similar neural activation patterns in the early stages, involving the activation and retrieval of long-term memory information based on contextual cues. The differences between the two primarily manifest in the middle and late stages, where the selection of humorous ideas requires inhibiting not only irrelevant or ordinary ideas, akin to creative generation but also novel yet non-humorous ideas. This study sheds light on the neurocognitive mechanisms of humor generation and provides insights into the cognitive parallels and distinctions between humor generation and creative generation.

Early Movement Restriction Affects FNDC5/Irisin and BDNF Levels in Rat Muscle and Brain.

Interaction with the environment appears necessary for the maturation of sensorimotor and cognitive functions in early life. In rats, a model of sensorimotor restriction (SMR) from postnatal day 1 (P1) to P28 has shown that low and atypical sensorimotor activities induced the perturbation of motor behavior due to muscle weakness and the functional disorganization of the primary somatosensory and motor cortices. In the present study, our objective was to understand how SMR affects the muscle-brain dialogue. We focused on irisin, a myokine secreted by skeletal muscles in response to exercise. FNDC5/irisin expression was determined in hindlimb muscles and brain structures by Western blotting, and irisin expression in blood and cerebrospinal fluid was determined using an ELISA assay at P8, P15, P21 and P28. Since irisin is known to regulate its expression, Brain-Derived Neurotrophic Factor (BDNF) levels were also measured in the same brain structures. We demonstrated that SMR increases FNDC5/irisin levels specifically in the soleus muscle (from P21) and also affects this protein expression in several brain structures (as early as P15). The BDNF level was increased in the hippocampus at P8. To conclude, SMR affects FNDC5/irisin levels in a postural muscle and in several brain regions and has limited effects on BDNF expression in the brain.

Opinion attribution improves motivation to exchange subjective opinions with humanoid robots.

In recent years, the development of robots that can engage in non-task-oriented dialogue with people, such as chat, has received increasing attention. This study aims to clarify the factors that improve the user's willingness to talk with robots in non-task oriented dialogues (e.g., chat). A previous study reported that exchanging subjective opinions makes such dialogue enjoyable and enthusiastic. In some cases, however, the robot's subjective opinions are not realistic, i.e., the user believes the robot does not have opinions, thus we cannot attribute the opinion to the robot. For example, if a robot says that alcohol tastes good, it may be difficult to imagine the robot having such an opinion. In this case, the user's motivation to exchange opinions may decrease. In this study, we hypothesize that regardless of the type of robot, opinion attribution affects the user's motivation to exchange opinions with humanoid robots. We examined the effect by preparing various opinions of two kinds of humanoid robots. The experimental result suggests that not only the users' interest in the topic but also the attribution of the subjective opinions to them influence their motivation to exchange opinions. Another analysis revealed that the android significantly increased the motivation when they are interested in the topic and do not attribute opinions, while the small robot significantly increased it when not interested and attributed opinions. In situations where there are opinions that cannot be attributed to humanoid robots, the result that androids are more motivating when users have the interests even if opinions are not attributed can indicate the usefulness of androids.

Disclosure following a medical error: lessons learned from a national initiative of workshops with patients, healthcare teams, and executives.

BACKGROUND: Despite the increase in disclosures of medical errors, transparency remains a challenge. Recognized barriers include shame, fear of litigation, disciplinary actions, and loss of patient trust. In 2018, the Israeli Ministry of Health initiated a series of workshops about disclosure of medical errors. The workshops involved medical center executives, healthcare providers, patients, and family members of patients who had previously been harmed by a medical error. This study presents the lessons learned about perceived challenges in disclosure of errors in 15 such workshops. METHODS: Data collection included participant observations in 15 workshops, full audio recordings of all of the workshops, and documentation of detailed field notes. Analysis was performed under thematic analysis guidelines. RESULTS: We identified four main themes: "Providers agree on the value of disclosure of a medical error to the patient"; "Emotional challenges of disclosure of medical error to patients"; "The medico-legal discourse challenges transparency"; and "Providers and patients call for a change in the culture regarding disclosure of medical errors". Participant observations indicated that the presence of a patient who had experienced a tragedy in another hospital, and who was willing to share it created an intimate atmosphere that enabled an open conversation between parties. CONCLUSION: The study shows the moral, human, and educational values of open discourse in a protective setting after the occurrence of a medical error. We believe that workshops like these may help foster a culture of institutional disclosure following medical errors. We recommend that the Ministry of Health extend such workshops to all healthcare facilities, establish guidelines and mandate training for skills in disclosure for all providers.

Balance and Change in Forensic Psychiatry.

The practice of forensic psychiatry requires balance; the forensic psychiatrist encounters the need for balance routinely and in a variety of areas. Balance is necessary for sound judgment and objectivity when striving for excellence in the field. It is also necessary to effectively balance a career in forensic psychiatry with one's personal life. The American Academy of Psychiatry and the Law (AAPL) has stressed the virtue of balance in the preamble of its ethics guidelines, noting the importance of balancing competing obligations to the individual and society. Keeping in mind the importance of balance will assist forensic psychiatry with the many challenges of a postinternet era, such as rapidly changing technology, culture, and society. A substantial challenge for forensic psychiatry, now and in the future, involves data overflow and the so-called big data explosion. Information now flows too fast and in such vast amounts that a single individual can no longer keep pace. Balance may be pursued by adapting and leveraging certain skills to confront these challenges more effectively. The current inflection point of rapid technological, social, and cultural change, stresses the importance of balance through teamwork, technology, and prioritizing civil discourse.

Exploring the potential of ChatGPT in medical dialogue summarization: a study on consistency with human preferences.

BACKGROUND: Telemedicine has experienced rapid growth in recent years, aiming to enhance medical efficiency and reduce the workload of healthcare professionals. During the COVID-19 pandemic in 2019, it became especially crucial, enabling remote screenings and access to healthcare services while maintaining social distancing. Online consultation platforms have emerged, but the demand has strained the availability of medical professionals, directly leading to research and development in automated medical consultation. Specifically, there is a need for efficient and accurate medical dialogue summarization algorithms to condense lengthy conversations into shorter versions focused on relevant medical facts. The success of large language models like generative pre-trained transformer (GPT)-3 has recently prompted a paradigm shift in natural language processing (NLP) research. In this paper, we will explore its impact on medical dialogue summarization. METHODS: We present the performance and evaluation results of two approaches on a medical dialogue dataset. The first approach is based on fine-tuned pre-trained language models, such as bert-based summarization (BERTSUM) and bidirectional auto-regressive Transformers (BART). The second approach utilizes a large language models (LLMs) GPT-3.5 with inter-context learning (ICL). Evaluation is conducted using automated metrics such as ROUGE and BERTScore. RESULTS: In comparison to the BART and ChatGPT models, the summaries generated by the BERTSUM model not only exhibit significantly lower ROUGE and BERTScore values but also fail to pass the testing for any of the metrics in manual evaluation. On the other hand, the BART model achieved the highest ROUGE and BERTScore values among all evaluated models, surpassing ChatGPT. Its ROUGE-1, ROUGE-2, ROUGE-L, and BERTScore values were 14.94%, 53.48%, 32.84%, and 6.73% higher respectively than ChatGPT's best results. However, in the manual evaluation by medical experts, the summaries generated by the BART model exhibit satisfactory performance only in the "Readability" metric, with less than 30% passing the manual evaluation in other metrics. When compared to the BERTSUM and BART models, the ChatGPT model was evidently more favored by human medical experts. CONCLUSION: On one hand, the GPT-3.5 model can manipulate the style and outcomes of medical dialogue summaries through various prompts. The generated content is not only better received than results from certain human experts but also more comprehensible, making it a promising avenue for automated medical dialogue summarization. On the other hand, automated evaluation mechanisms like ROUGE and BERTScore fall short in fully assessing the outputs of large language models like GPT-3.5. Therefore, it is necessary to research more appropriate evaluation criteria.