Dynamic Topic Model for Quantitative Estimation of Conversation Process During Psychotherapy
-
- Yokoyama Satoshi
- Graduate School of Biomedical and Health Sciences, Hiroshima University
-
- Takagaki Koki
- Health Service Center, Hiroshima University
-
- Kambara Kohei
- Graduate School of Humanities and Social Sciences, Hiroshima University
-
- Jinnin Ran
- Graduate School of Biomedical and Health Sciences, Hiroshima University
-
- Okamoto Yasumasa
- Graduate School of Biomedical and Health Sciences, Hiroshima University
Bibliographic Information
- Other Title
-
- 動的トピックモデルを用いた心理療法における会話プロセスの量的推定
- ドウテキ トピックモデル オ モチイタ シンリ リョウホウ ニ オケル カイワ プロセス ノ リョウテキ スイテイ
Search this article
Abstract
<p>Limited evidence has shown how the therapeutic effects of psychotherapies have been obtained compared to abundant evidence based on the changes in the clinical outcome scores. Psychotherapy depends on interactive therapeutic conversations. Hence, topic models have recently attracted attention for linguistic information as data-driven computational approaches can produce objective and reproducible models. This study examined whether a dynamic topic model with a time-series structure could extract treatment session content from single-case conversation data during a structured behavioral activation program. We extracted four potential topics during the treatment sessions. The quantitative transition process reflected the program treatment contents. This is the first study to apply the dynamic topic model for conversation during psychotherapy, which quantifies the actual treatment process. The results show cumulative evidence of the effects of psychotherapy.</p>
Journal
-
- Japanese Journal of Behavioral and Cognitive Therapies
-
Japanese Journal of Behavioral and Cognitive Therapies 47 (3), 295-306, 2021-09-30
Japanese Association for Behavioral and Cognitive Therapies( JABCT )
- Tweet
Details 詳細情報について
-
- CRID
- 1390290769928224384
-
- NII Article ID
- 130008141039
-
- NII Book ID
- AA12821633
-
- ISSN
- 24339040
- 24339075
-
- NDL BIB ID
- 031892742
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- NDL
- CiNii Articles
- KAKEN
-
- Abstract License Flag
- Disallowed