Automated Empathy Detection for Oncology Encounters

Chen, Zhuohao; Gibson, James; Chiu, Ming-Chang; Hu, Qiaohong; Knight, Tara K.; Meeker, Daniella; Tulsky, James A.; Pollak, Kathryn I.; Narayanan, Shrikanth

doi:10.1109/ichi48887.2020.9374402

Cited by 4 publications

(4 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, many popular video conferencing services already incorporate tools that automate the detection of speaker turns, and such services have exploded in popularity in the wake of the Covid-19 global pandemic. Ongoing advances in the automated detection of conversational features including speaker recognition [64,65], emotion [66,67], conversational pauses [54], empathy [68,69], gaze patterns [70], and word recognition [71], will facilitate real-time analysis and contextualization of CODYMs. Ultimately, we foresee a fully-automated pipeline for CODYM analyses, with no compromise to the privacy of conversational content.…”

Section: Discussionmentioning

confidence: 99%

A general model of conversational dynamics and an example application in serious illness communication

et al. 2021

View full text Add to dashboard Cite

Conversation has been a primary means for the exchange of information since ancient times. Understanding patterns of information flow in conversations is a critical step in assessing and improving communication quality. In this paper, we describe COnversational DYnamics Model (CODYM) analysis, a novel approach for studying patterns of information flow in conversations. CODYMs are Markov Models that capture sequential dependencies in the lengths of speaker turns. The proposed method is automated and scalable, and preserves the privacy of the conversational participants. The primary function of CODYM analysis is to quantify and visualize patterns of information flow, concisely summarized over sequential turns from one or more conversations. Our approach is general and complements existing methods, providing a new tool for use in the analysis of any type of conversation. As an important first application, we demonstrate the model on transcribed conversations between palliative care clinicians and seriously ill patients. These conversations are dynamic and complex, taking place amidst heavy emotions, and include difficult topics such as end-of-life preferences and patient values. We use CODYMs to identify normative patterns of information flow in serious illness conversations, show how these normative patterns change over the course of the conversations, and show how they differ in conversations where the patient does or doesn’t audibly express anger or fear. Potential applications of CODYMs range from assessment and training of effective healthcare communication to comparing conversational dynamics across languages, cultures, and contexts with the prospect of identifying universal similarities and unique “fingerprints” of information flow.

show abstract

Section: Discussionmentioning

confidence: 99%

A general model of conversational dynamics and an example application in serious illness communication

et al. 2021

View full text Add to dashboard Cite

show abstract

“…For example, many popular video conferencing services already incorporate tools that automate the detection of speaker turns, and such services have exploded in popularity in the wake of the Covid-19 global pandemic. Ongoing advances in the automated detection of conversational features including speaker recognition [80,81], emotion [82,83], conversational pauses [57], empathy [84,85], gaze patterns [86], and word recognition [87], will facilitate real-time analysis and contextualization of CODYMs. Ultimately, we foresee a fully-automated pipeline for CODYM analyses, with no compromise to the privacy of conversational content.…”

Section: Discussionmentioning

confidence: 99%

A General Model of Conversational Dynamics and an Example Application in Serious Illness Communication

Clarfeld,

Gramling,

Rizzo

et al. 2020

Preprint

View full text Add to dashboard Cite

Conversation has been a primary means for the exchange of information since ancient times. Understanding patterns of information flow in conversations is a critical step in assessing and improving communication quality. In this paper, we describe COnversational DYnamics Model (CODYM) analysis, a novel approach for studying patterns of information flow in conversations. CODYMs are Markov Models that capture sequential dependencies in the lengths of speaker turns. The proposed method is automated and scalable, and preserves the privacy of the conversational participants. The primary function of CODYM analysis is to quantify and visualize patterns of information flow, concisely summarized over sequential turns from one or more conversations. Our approach is general and complements existing methods, providing a new tool for use in the analysis of any type of conversation. As an important first application, we demonstrate the model on transcribed conversations between palliative care clinicians and seriously ill patients. These conversations are dynamic and complex, taking place amidst heavy emotions, and include difficult topics such as end-of-life preferences and patient values. We perform a versatile set of CODYM analyses that (a) establish the validity of the model by confirming known patterns of conversational turn-taking and word usage, (b) identify normative patterns of information flow in serious illness conversations, and (c) show how these patterns vary across narrative time and differ under expressions of anger, fear and sadness. Potential applications of CODYMs range from assessment and training of effective healthcare communication to comparing conversational dynamics across language and culture, with the prospect of identifying universal similarities and unique "fingerprints" of information flow.

show abstract

“…Empathy detection, one of a series of empathy tasks, has been widely studied by many researchers (Hosseini and Caragea, 2021a;Chen et al, 2020). Currently, the task involves two types of research: analyzing empathy from text (Yang et al, 2019;Buechel et al, 2018;Sedoc et al, 2020;Ghosh et al, 2022), and from spoken dialogues (Fung et al, 2016;Kim et al, 2022;Alam et al, 2018;Pérez-Rosas et al, 2017;Ayshabi and Idicula, 2021).…”

Section: Empathy Detectionmentioning

confidence: 99%

“…Therefore, it is worthwhile to detect the empathetic direction of dialogue utterances. In recent years, researchers have studied empathy detection in various fields, such as mental health support (Sharma et al, 2020 Jurgens, 2020), empathetic expression understanding in newswire (Buechel et al, 2018), medical and healthcare (Khanpour et al, 2017;Hosseini and Caragea, 2021a;Chen et al, 2020;Wijaya et al, 2023), human-computer interaction (Virvou and Katsionis, 2004;Xie and Pu, 2021;Gao et al, 2021;Samad et al, 2022), etc. Currently, millions of people seek psychological support by expressing their emotions in online health communities and look forward to receiving support from peers who may have had similar experiences and can understand their feelings.…”

Section: Introductionmentioning

confidence: 99%

Empathy Intent Drives Empathy Detection

Jiang,

Wu,

Mao

et al. 2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Empathy plays an important role in the human dialogue. Detecting the empathetic direction expressed by the user is necessary for empathetic dialogue systems because it is highly relevant to understanding the user's needs. Several studies have shown that empathy intent information improves the ability to response capacity of empathetic dialogue. However, the interaction between empathy detection and empathy intent recognition has not been explored. To this end, we invite 3 experts to manually annotate the healthy empathy detection datasets IEMPATHIZE and TwittEmp with 8 empathy intent labels, and perform joint training for the two tasks. Empirical study has shown that the introduction of empathy intent recognition task can improve the accuracy of empathy detection task, and we analyze possible reasons for this improvement. To make joint training of the two tasks more challenging, we propose a novel framework, Cascaded Label Signal Network, which uses the cascaded interactive attention module and the label signal enhancement module to capture feature exchange information between empathy and empathy intent representations. Experimental results show that our framework outperforms all baselines under both settings on the two datasets. 1

show abstract

Automated Empathy Detection for Oncology Encounters

Cited by 4 publications

References 47 publications

A general model of conversational dynamics and an example application in serious illness communication

A general model of conversational dynamics and an example application in serious illness communication

A General Model of Conversational Dynamics and an Example Application in Serious Illness Communication

Empathy Intent Drives Empathy Detection

Contact Info

Product

Resources

About