A New Method of Subjective Evaluation Using Visual Analog Scale for Small Sample Data Analysis

• Item type: Trans(1)
• 公開日: 2021-04-15
• タイトル: A New Method of Subjective Evaluation Using Visual Analog Scale for Small Sample Data Analysis
• タイトル / 言語: en
• タイトル: A New Method of Subjective Evaluation Using Visual Analog Scale for Small Sample Data Analysis
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: [特集号投稿論文] visual analog scale, subjective evaluation, small sample, talking robot
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_6501
• 資源タイプ: journal article
• 著者所属: Department of Creative Engineering, National Institute of Technology (KOSEN), Kitakyushu College
• 著者所属: School of Health Sciences at Odawara, International University of Health and Welfare
• 著者所属: Department of Production Systems Engineering, National Institute of Technology (KOSEN), Hakodate College
• 著者所属: Department of Human-Oriented Information Systems Engineering, National Institute of Technology (KOSEN), Kumamoto College
• 著者所属: Department of Creative Engineering, National Institute of Technology (KOSEN), Kitakyushu College
• 著者所属(英): en
• 著者所属(英): Department of Creative Engineering, National Institute of Technology (KOSEN), Kitakyushu College
• 著者所属(英): en
• 著者所属(英): School of Health Sciences at Odawara, International University of Health and Welfare
• 著者所属(英): en
• 著者所属(英): Department of Production Systems Engineering, National Institute of Technology (KOSEN), Hakodate College
• 著者所属(英): en
• 著者所属(英): Department of Human-Oriented Information Systems Engineering, National Institute of Technology (KOSEN), Kumamoto College
• 著者所属(英): en
• 著者所属(英): Department of Creative Engineering, National Institute of Technology (KOSEN), Kitakyushu College
• 著者名: Naruki, Shirahama; Satoshi, Watanabe; Kenji, Moriya; Kazuhiro, Koshi; Keiji, Matsumoto
• 著者名(英): Naruki, Shirahama; Satoshi, Watanabe; Kenji, Moriya; Kazuhiro, Koshi; Keiji, Matsumoto
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: The Likert Scale (LS) is more commonly used in the psychological and affective engineering field. However, LS has some problems, such as the fact that it can only be used for non-parametric analysis if it cannot be treated as an interval measure and is susceptible to biases such as the central tendency and the halo effect. In this study, we propose an analysis method using the Visual Analog Scale (VAS) in which a point marked on a straight line is the evaluation value instead of a five or seven-point scale. The VAS allows us to identify trends in the distribution of data, even in small samples. We visualize the VAS experimental results by overlaying box plots and beeswarm plots to visually grasp the data's distributional trends, even for small samples. We experimented with 30 subjects on conversations with a talking toy robot. We investigated the user's emotions from the conversation with a robot and whether it relates to the conversation's smoothness. The number of questions was 10, and two cases of smooth and non-smooth conversations with the talking robot were evaluated using the VAS method, respectively. The hierarchical clustering results showed that a group of questions expected to show a similar trend was classified into the same cluster. Parametric tests were also performed on data groups following a normal distribution.; ------------------------------; This is a preprint of an article intended for publication Journal of; Information Processing(JIP). This preprint should not be cited. This; article should be cited as: Journal of Information Processing Vol.29(2021) (online); ------------------------------
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: The Likert Scale (LS) is more commonly used in the psychological and affective engineering field. However, LS has some problems, such as the fact that it can only be used for non-parametric analysis if it cannot be treated as an interval measure and is susceptible to biases such as the central tendency and the halo effect. In this study, we propose an analysis method using the Visual Analog Scale (VAS) in which a point marked on a straight line is the evaluation value instead of a five or seven-point scale. The VAS allows us to identify trends in the distribution of data, even in small samples. We visualize the VAS experimental results by overlaying box plots and beeswarm plots to visually grasp the data's distributional trends, even for small samples. We experimented with 30 subjects on conversations with a talking toy robot. We investigated the user's emotions from the conversation with a robot and whether it relates to the conversation's smoothness. The number of questions was 10, and two cases of smooth and non-smooth conversations with the talking robot were evaluated using the VAS method, respectively. The hierarchical clustering results showed that a group of questions expected to show a similar trend was classified into the same cluster. Parametric tests were also performed on data groups following a normal distribution.; ------------------------------; This is a preprint of an article intended for publication Journal of; Information Processing(JIP). This preprint should not be cited. This; article should be cited as: Journal of Information Processing Vol.29(2021) (online); ------------------------------
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA12894091
• 書誌情報: 情報処理学会論文誌デジタルプラクティス（DP）; 巻 2, 号 2, 発行日 2021-04-15
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2435-6484
• 出版者 / 言語: ja
• 出版者: 情報処理学会