A multi-modal dialogue analysis method for medical interviews based on design of interaction corpus

Koyama, Yoshinori; Sawamoto, Yuichi; Hirano, Yasushi; Shoji, K.; Mase, Kenji; Suzuki, Tomio; Katsuyama, Kimiko; Yamauchi, Kazunobu

doi:10.1007/s00779-010-0289-5

Cited by 3 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Koyama et al [14] established a new preference prediction model by analyzing user dialogues and online interactions, the experiment confirmed that the model could improve the accuracy of interest mining. Zhou et al [15] used topic model to predict the similarity of users to publish content, and the experiment proved that the model could more accurately infer the contents of the similarity between users.…”

Section: Related Workmentioning

confidence: 92%

GPOGC: Gaussian Pigeon-Oriented Graph Clustering Algorithm for Social Networks Cluster

Sun

Yin

et al. 2019

IEEE Access

View full text Add to dashboard Cite

As the continuous development of mobile social networks, the structure of the mobile social network increasingly becomes complex. It not only speeds up information transmission between people but also expands the scope of information exchange, which has become an essential and important social media in people's social life. How to effectively identify and classify these online communities has important practical significance for the study of social networks. Correctly detecting the community structure of mobile social networks can not only improve the accuracy of friend recommendation, link prediction, service user positioning, product marketing, and other aspects but also provide an important basis for the monitoring of online public opinion. But the traditional social network cluster method based on the trust degree mainly calculates the user trust by analyzing the interactive feedback information between users. This method cannot effectively solve the ''cold start'' problem in the trust calculation process, that is, for the new network node, the trust value of this node cannot be accurately measured due to the lack of interaction with other nodes. Focusing on this problem, we propose a Gaussian pigeon-oriented graph clustering algorithm for social networks' cluster in this paper. A graph model is first built. Then, an efficient K-medoid algorithm is utilized to search the user center in all groups. The Gaussian pigeon algorithm is used to search the similarity between each user and the central user. Users that meet the similarity threshold are divided into the same user group. Finally, the simulation results show that the proposed method has better cluster effect than other state-ofthe-art social networks' clustering approaches.INDEX TERMS Social network, Gaussian pigeon algorithm, graph clustering, K-medoid algorithm.

show abstract

Section: Related Workmentioning

confidence: 92%

GPOGC: Gaussian Pigeon-Oriented Graph Clustering Algorithm for Social Networks Cluster

Sun

Yin

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…For instance, hypotheses on the occurrence of these patterns have been investigated in the context of the analysis of voice expressions to derive dialog acts [Yu et al, 2012] and the discrimination among brainstorming sessions and decision making sessions in meetings [Jayagopi et al, 2012]. Analysis of event composition has also been explored in the context of interviews between physicians and patients [Koyama et al, 2010]. Much of this research has been based on machine learning methods and data mining in order to derive complex events, since a set of basic events is available.…”

Section: Investigation Of Methods For Derivation Of Events With High mentioning

confidence: 99%

“…change of slides, live annotations, speech turn taking, primitive gestures, addressing, nodding, etc.) [Koyama et al, 2010;Terken and Sturm, 2010] to high-level behaviors (such as decisions, disagreement, dominance, extroversion, social roles, competition, personality states, etc.) [Gatica-Perez, 2009;Popescu-Belis et al, 2012].…”

Section: Context and Motivationmentioning

confidence: 99%

“…For instance, hypotheses regarding the occurrence of these patterns have been investigated in the analysis of voice utterances to derive dialogue acts [Yu et al, 2012] and the discrimination among brainstorming and decision-making discussions [Jayagopi et al, 2012]. The analysis of composite interaction patterns have also been investigated in the context of recordings from doctor-patient interviews [Koyama et al, 2010]. These research results suggest the feasibility of combining low-level interaction cues in order to make sense of specific events in small group activities, opening up possibilities for better session browsing mechanisms.…”

Section: Chaptermentioning

confidence: 99%

See 1 more Smart Citation

Models and operators for extension of active multimedia documents via annotations

Martins¹

View full text Add to dashboard Cite

Primarily, I acknowledge my advisor, Prof. Maria da Graça C. Pimentel, for the continuous support and guidance during the development of this dissertation. Thanks for helping me make this dissertation possible. I also thank CNPq for financing my research. Thanks to the evaluation committee for the important insights that contributed to improve the final version of this text. Thanks to research colleagues that have collaborated, directly or indirectly, to the discussions and experiments that lead to this research: Didier Vega-Oliveros, Lílian Oliveira e Diogo Pedrosa. I extend acknowledgements to the researchers from the SEN-5 group at CWI, who, during my internship with them, have contributed in important ways to my research: Pablo Cesar, Rodrigo Guimarães, Jack Jansen e Dick Bulterman. Finally, I thank my family for the support through this journey. First, my mother, Arlete, for standing up for me along my entire academic career and believing in my choices. My grandmother, Seide, whose early support in my education made it possible that I reached this milestone. In addition, Mario Liziér, for the understanding, support, and encouragement whenever I needed.

show abstract

Browsing interaction events in recordings of small group activities via multimedia operators

Martins

Pimentel

2012

Proceedings of the 18th Brazilian Symposium on Multimedia and the Web

View full text Add to dashboard Cite

A multi-modal dialogue analysis method for medical interviews based on design of interaction corpus

Cited by 3 publications

References 16 publications

GPOGC: Gaussian Pigeon-Oriented Graph Clustering Algorithm for Social Networks Cluster

GPOGC: Gaussian Pigeon-Oriented Graph Clustering Algorithm for Social Networks Cluster

Models and operators for extension of active multimedia documents via annotations

Browsing interaction events in recordings of small group activities via multimedia operators

Contact Info

Product

Resources

About