Abstract | ||
---|---|---|
This paper presents a process to build a classifier in a data-driven way for recognizing engagement of children in a robot-based math quiz game. The process consists of collecting video recordings from HRI experiments; annotating the social signals and engagement states via video analysis; extracting feature vectors from the annotations and training classifiers. We conducted an experiment with 7 participants of 10 -- 11 years of age using an android robot EveR-4. With three coders annotating the video recordings and extracting features by snapshot model with 1-second time window, we achieved 84.83% recall performance. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1145/2559636.2563687 | HRI |
Keywords | DocType | ISSN |
automated engagement recognizer,recall performance,engagement state,robot-based math quiz game,video recording,1-second time window,video analysis,snapshot model,android robot ever-4,hri experiment,feature vector | Conference | 2167-2121 |
ISBN | Citations | PageRank |
978-1-4503-2658-2 | 3 | 0.52 |
References | Authors | |
4 | 10 |
Name | Order | Citations | PageRank |
---|---|---|---|
Minsu Jang | 1 | 102 | 11.99 |
Cheonshu Park | 2 | 9 | 2.68 |
Hyun-Seung Yang | 3 | 49 | 6.48 |
Jaehong Kim | 4 | 194 | 22.43 |
Young-Jo Cho | 5 | 149 | 20.92 |
Dongwook Lee | 6 | 418 | 62.32 |
Hye-Kyung Cho | 7 | 15 | 4.52 |
Young-Ae Kim | 8 | 3 | 0.52 |
Kyoungwha Chae | 9 | 3 | 0.52 |
Byeong-Kyu Ahn | 10 | 4 | 1.57 |