Seung-Moo Lee

Emotions play a key role in collaborative software practices like pair programming. In this case study, we analyze pair programming videos to assess whether Large Language Models (LLMs) can serve as pair programming partners. We adapt the EmpatheticDialogues benchmark to create scenarios that simulate how an LLM responds in emotional moments in pair programming. We find that LLMs generally match the level of empathy humans provide in emotional moments during pair programming. However, they sometimes get lost in conversational dynamics and miss the big picture, and prioritize task progression over discussion. Our findings highlight both the potential and current limitations of LLMs in emotionally sensitive programming contexts.

Background: Social anxiety disorder (SAD) is the fear of social situations where a person anticipates being evaluated negatively. Changes in autonomic response patterns are related to the expression of anxiety symptoms. Virtual reality (VR) sickness can inhibit VR experiences. Objective: This study aimed to predict the severity of specific anxiety symptoms and VR sickness in patients with SAD, using machine learning based on in situ autonomic physiological signals (heart rate and galvanic skin response) during VR treatment sessions. Methods: This study included 32 participants with SAD taking part in 6 VR sessions. During each VR session, the heart rate and galvanic skin response of all participants were measured in real time. We assessed specific anxiety symptoms using the Internalized Shame Scale (ISS) and the Post-Event Rumination Scale (PERS), and VR sickness using the Simulator Sickness Questionnaire (SSQ) during 4 VR sessions (#1, #2, #4, and #6). Logistic regression, random forest, and naïve Bayes classification classified and predicted the severity groups in the ISS, PERS, and SSQ subdomains based on in situ autonomic physiological signal data. Results: The severity of SAD was predicted with 3 machine learning models. According to the F1 score, the highest prediction performance among each domain for severity was determined. The F1 score of the ISS mistake anxiety subdomain was 0.8421 using the logistic regression model, that of the PERS positive subdomain was 0.7619 using the naïve Bayes classifier, and that of total VR sickness was 0.7059 using the random forest model. Conclusions: This study could predict specific anxiety symptoms and VR sickness during VR intervention by autonomic physiological signals alone in real time. Machine learning models can predict the severe and nonsevere psychological states of individuals based on in situ physiological signal data during VR interventions for real-time interactive services. These models can support the diagnosis of specific anxiety symptoms and VR sickness with minimal participant bias. Trial Registration: Clinical Research Information Service KCT0003854; https://cris.nih.go.kr/cris/search/detailSearch.do/13508

Background: Although it has been well demonstrated that the efficacy of virtual reality therapy for social anxiety disorder is comparable to that of traditional cognitive behavioral therapy, little is known about the effect of virtual reality on pathological self-referential processes in individuals with social anxiety disorder. Objective: We aimed to determine changes in self-referential processing and their neural mechanisms following virtual reality treatment. Methods: We recruited participants with and without a primary diagnosis of social anxiety disorder to undergo clinical assessments (Social Phobia Scale and Post-Event Rumination Scale) and functional magnetic resonance imaging (fMRI) scans. Participants with social anxiety disorder received virtual reality–based exposure treatment for 6 sessions starting immediately after baseline testing. After the sixth session, participants with social anxiety disorder completed follow-up scans during which they were asked to judge whether a series of words (positive, negative, neutral) was relevant to them. Results: Of 25 individuals with social anxiety disorder who participated in the study, 21 completed the sessions and follow-up; 22 control individuals also participated. There were no significant differences in age (P=.36), sex (P=.71), or handedness (P=.51) between the groups. Whole-brain analysis revealed that participants in the social anxiety disorder group had increased neural responses during positive self-referential processing in the medial temporal and frontal cortexes compared with those in the control group. Participants in the social anxiety disorder group also showed increased left insular activation and decreased right middle frontal gyrus activation during negative self-referential processing. After undergoing virtual reality–based therapy, overall symptoms of the participants with social anxiety disorder were reduced, and these participants exhibited greater activity in a brain regions responsible for self-referential and autobiographical memory processes while viewing positive words during postintervention fMRI scans. Interestingly, the greater the blood oxygen level dependent changes related to positive self-referential processing, the lower the tendency to ruminate on the negative events and the lower the social anxiety following the virtual reality session. Compared with that at baseline, higher activation was also found within broad somatosensory areas in individuals with social anxiety disorder during negative self-referential processing following virtual reality therapy. Conclusions: These fMRI findings might reflect the enhanced physiological and cognitive processing in individuals with social anxiety disorder in response to self-referential information. They also provide neural evidence of the effect of virtual reality exposure therapy on social anxiety and self-derogation.

BACKGROUND Although it has been well demonstrated that the efficacy of virtual reality therapy for social anxiety disorder is comparable to that of traditional cognitive behavioral therapy, little is known about the effect of virtual reality on pathological self-referential processes in individuals with social anxiety disorder. OBJECTIVE We aimed to determine changes in self-referential processing and their neural mechanisms following virtual reality treatment. METHODS We recruited participants with and without a primary diagnosis of social anxiety disorder to undergo clinical assessments (Social Phobia Scale and Post-Event Rumination Scale) and functional magnetic resonance imaging (fMRI) scans. Participants with social anxiety disorder received virtual reality–based exposure treatment for 6 sessions starting immediately after baseline testing. After the sixth session, participants with social anxiety disorder completed follow-up scans during which they were asked to judge whether a series of words (positive, negative, neutral) was relevant to them. RESULTS Of 25 individuals with social anxiety disorder who participated in the study, 21 completed the sessions and follow-up; 22 control individuals also participated. There were no significant differences in age (P=.36), sex (P=.71), or handedness (P=.51) between the groups. Whole-brain analysis revealed that participants in the social anxiety disorder group had increased neural responses during positive self-referential processing in the medial temporal and frontal cortexes compared with those in the control group. Participants in the social anxiety disorder group also showed increased left insular activation and decreased right middle frontal gyrus activation during negative self-referential processing. After undergoing virtual reality–based therapy, overall symptoms of the participants with social anxiety disorder were reduced, and these participants exhibited greater activity in a brain regions responsible for self-referential and autobiographical memory processes while viewing positive words during postintervention fMRI scans. Interestingly, the greater the blood oxygen level dependent changes related to positive self-referential processing, the lower the tendency to ruminate on the negative events and the lower the social anxiety following the virtual reality session. Compared with that at baseline, higher activation was also found within broad somatosensory areas in individuals with social anxiety disorder during negative self-referential processing following virtual reality therapy. CONCLUSIONS These fMRI findings might reflect the enhanced physiological and cognitive processing in individuals with social anxiety disorder in response to self-referential information. They also provide neural evidence of the effect of virtual reality exposure therapy on social anxiety and self-derogation.

Background: Social anxiety disorder (SAD) is characterized by excessive fear of negative evaluation and humiliation in social interactions and situations. Virtual reality (VR) treatment is a promising intervention option for SAD.Objective: The purpose of this study was to create a participatory and interactive VR intervention for SAD. Treatment progress, including the severity of symptoms and the cognitive and emotional aspects of SAD, was analyzed to evaluate the effectiveness of the intervention.Methods: In total, 32 individuals with SAD and 34 healthy control participants were enrolled in the study through advertisements for online bulletin boards at universities. A VR intervention was designed consisting of three stages (introduction, core, and finishing) and three difficulty levels (easy, medium, and hard) that could be selected by the participants. The core stage was the exposure intervention in which participants engaged in social situations. The effectiveness of treatment was assessed through Beck Anxiety inventory (BAI), State‐Trait Anxiety Inventory (STAI), Internalized Shame Scale (ISS), Post-Event Rumination Scale (PERS), Social Phobia Scale (SPS), Social Interaction Anxiety Scale (SIAS), Brief-Fear of Negative Evaluation Scale (BFNE), and Liebowitz Social Anxiety Scale (LSAS).Results: In the SAD group, scores on the BAI (F=4.616, P=.009), STAI-Trait (F=4.670, P=.004), ISS (F=6.924, P=.001), PERS-negative (F=1.008, P<.001), SPS (F=8.456, P<.001), BFNE (F=6.117, P=.004), KSAD (F=13.259, P<.001), and LSAS (F=4.103, P=.009) significantly improved over the treatment process. Compared with the healthy control group before treatment, the SAD group showed significantly higher scores on all scales (P<.001), and these significant differences persisted even after treatment (P<.001). In the comparison between the VR treatment responder and nonresponder subgroups, there was no significant difference across the course of the VR session.Conclusions: These findings indicated that a participatory and interactive VR intervention had a significant effect on alleviation of the clinical symptoms of SAD, confirming the usefulness of VR for the treatment of SAD. VR treatment is expected to be one of various beneficial therapeutic approaches in the future.Trial Registration: Clinical Research Information Service (CRIS) KCT0003854; https://cris.nih.go.kr/cris/search/search_result_st01.jsp?seq=13508

BACKGROUND Social anxiety disorder (SAD) is characterized by excessive fear of negative evaluation and humiliation in social interactions and situations. Virtual reality (VR) treatment is a promising intervention option for SAD. OBJECTIVE The purpose of this study was to create a participatory and interactive VR intervention for SAD. Treatment progress, including the severity of symptoms and the cognitive and emotional aspects of SAD, was analyzed to evaluate the effectiveness of the intervention. METHODS In total, 32 individuals with SAD and 34 healthy control participants were enrolled in the study through advertisements for online bulletin boards at universities. A VR intervention was designed consisting of three stages (introduction, core, and finishing) and three difficulty levels (easy, medium, and hard) that could be selected by the participants. The core stage was the exposure intervention in which participants engaged in social situations. The effectiveness of treatment was assessed through Beck Anxiety inventory (BAI), State‐Trait Anxiety Inventory (STAI), Internalized Shame Scale (ISS), Post-Event Rumination Scale (PERS), Social Phobia Scale (SPS), Social Interaction Anxiety Scale (SIAS), Brief-Fear of Negative Evaluation Scale (BFNE), and Liebowitz Social Anxiety Scale (LSAS). RESULTS In the SAD group, scores on the BAI (F=4.616, P=.009), STAI-Trait (F=4.670, P=.004), ISS (F=6.924, P=.001), PERS-negative (F=1.008, P<.001), SPS (F=8.456, P<.001), BFNE (F=6.117, P=.004), KSAD (F=13.259, P<.001), and LSAS (F=4.103, P=.009) significantly improved over the treatment process. Compared with the healthy control group before treatment, the SAD group showed significantly higher scores on all scales (P<.001), and these significant differences persisted even after treatment (P<.001). In the comparison between the VR treatment responder and nonresponder subgroups, there was no significant difference across the course of the VR session. CONCLUSIONS These findings indicated that a participatory and interactive VR intervention had a significant effect on alleviation of the clinical symptoms of SAD, confirming the usefulness of VR for the treatment of SAD. VR treatment is expected to be one of various beneficial therapeutic approaches in the future. CLINICALTRIAL Clinical Research Information Service (CRIS) KCT0003854; https://cris.nih.go.kr/cris/search/search_result_st01.jsp?seq=13508