Presentation skills estimation based on video and kinect data analysis

Vanessa Echeverría; Allan Avendaño; Katherine Chiluiza; Aníbal Vásquez; Xavier Ochoa

doi:10.1145/2666633.2666641

Presentation skills estimation based on video and kinect data analysis

Vanessa Echeverría, Allan Avendaño, Katherine Chiluiza, Aníbal Vásquez, Xavier Ochoa

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

40 Citations (Scopus)

Abstract

This paper identifies, by means of video and Kinect data, a set of predictors that estimate the presentation skills of 448 individual students. Two evaluation criteria were predicted: eye contact and posture and body language. Machine-learning evaluations resulted in models that predicted the perfor- mance level (good or poor) of the presenters with 68% and 63% of correctly classified instances, for eye contact and postures and body language criteria, respectively. Furthermore, the results suggest that certain features, such as arms movement and smoothness, provide high significance on predicting the level of development for presentation skills. The paper finishes with conclusions and related ideas for future work.

Original language	English
Title of host publication	MLA 2014 - Proceedings of the 2014 ACM Multimodal Learning Analytics Workshop and Grand Challenge, Co-located with ICMI 2014
Publisher	Association for Computing Machinery (ACM)
Pages	53-60
Number of pages	8
ISBN (Electronic)	9781450304887
DOIs	https://doi.org/10.1145/2666633.2666641
Publication status	Published - 12 Nov 2014
Externally published	Yes
Event	Multimodal Learning Analytics Workshop and Grand Challenges 2014 - Istanbul, Türkiye Duration: 12 Nov 2014 → 12 Nov 2014 Conference number: 3rd http://icmi.acm.org.ezproxy.lib.monash.edu.au/2014/

Workshop

Workshop	Multimodal Learning Analytics Workshop and Grand Challenges 2014
Abbreviated title	MLA 2014
Country/Territory	Türkiye
City	Istanbul
Period	12/11/14 → 12/11/14
Other	Event = 16th ACM International Conference on Multimodal Interaction, ICMI 2014 - Istanbul, Turkey Duration: Nov 12 2014 → Nov 16 2014 Proceedings title = ICMI 2014 - Proceedings of the 2014 International Conference on Multimodal Interaction
Internet address	http://icmi.acm.org.ezproxy.lib.monash.edu.au/2014/

Keywords

Multimodal
Presentation skills
Video features

Access to Document

10.1145/2666633.2666641

Cite this

Echeverría, V., Avendaño, A., Chiluiza, K., Vásquez, A., & Ochoa, X. (2014). Presentation skills estimation based on video and kinect data analysis. In MLA 2014 - Proceedings of the 2014 ACM Multimodal Learning Analytics Workshop and Grand Challenge, Co-located with ICMI 2014 (pp. 53-60). Association for Computing Machinery (ACM). https://doi.org/10.1145/2666633.2666641

@inproceedings{9413fd6c2ee542c79d14942e1923f93e,

title = "Presentation skills estimation based on video and kinect data analysis",

abstract = "This paper identifies, by means of video and Kinect data, a set of predictors that estimate the presentation skills of 448 individual students. Two evaluation criteria were predicted: eye contact and posture and body language. Machine-learning evaluations resulted in models that predicted the perfor- mance level (good or poor) of the presenters with 68% and 63% of correctly classified instances, for eye contact and postures and body language criteria, respectively. Furthermore, the results suggest that certain features, such as arms movement and smoothness, provide high significance on predicting the level of development for presentation skills. The paper finishes with conclusions and related ideas for future work.",

keywords = "Multimodal, Presentation skills, Video features",

author = "Vanessa Echeverr{\'i}a and Allan Avenda{\~n}o and Katherine Chiluiza and An{\'i}bal V{\'a}squez and Xavier Ochoa",

note = "Publisher Copyright: {\textcopyright} 2014 ACM.; Multimodal Learning Analytics Workshop and Grand Challenges 2014, MLA 2014 ; Conference date: 12-11-2014 Through 12-11-2014",

year = "2014",

month = nov,

day = "12",

doi = "10.1145/2666633.2666641",

language = "English",

pages = "53--60",

booktitle = "MLA 2014 - Proceedings of the 2014 ACM Multimodal Learning Analytics Workshop and Grand Challenge, Co-located with ICMI 2014",

publisher = "Association for Computing Machinery (ACM)",

address = "United States of America",

url = "http://icmi.acm.org.ezproxy.lib.monash.edu.au/2014/",

}

Echeverría, V, Avendaño, A, Chiluiza, K, Vásquez, A & Ochoa, X 2014, Presentation skills estimation based on video and kinect data analysis. in MLA 2014 - Proceedings of the 2014 ACM Multimodal Learning Analytics Workshop and Grand Challenge, Co-located with ICMI 2014. Association for Computing Machinery (ACM), pp. 53-60, Multimodal Learning Analytics Workshop and Grand Challenges 2014, Istanbul, Türkiye, 12/11/14. https://doi.org/10.1145/2666633.2666641

Presentation skills estimation based on video and kinect data analysis. / Echeverría, Vanessa; Avendaño, Allan; Chiluiza, Katherine et al.
MLA 2014 - Proceedings of the 2014 ACM Multimodal Learning Analytics Workshop and Grand Challenge, Co-located with ICMI 2014. Association for Computing Machinery (ACM), 2014. p. 53-60.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Presentation skills estimation based on video and kinect data analysis

AU - Echeverría, Vanessa

AU - Avendaño, Allan

AU - Chiluiza, Katherine

AU - Vásquez, Aníbal

AU - Ochoa, Xavier

N1 - Conference code: 3rd

PY - 2014/11/12

Y1 - 2014/11/12

N2 - This paper identifies, by means of video and Kinect data, a set of predictors that estimate the presentation skills of 448 individual students. Two evaluation criteria were predicted: eye contact and posture and body language. Machine-learning evaluations resulted in models that predicted the perfor- mance level (good or poor) of the presenters with 68% and 63% of correctly classified instances, for eye contact and postures and body language criteria, respectively. Furthermore, the results suggest that certain features, such as arms movement and smoothness, provide high significance on predicting the level of development for presentation skills. The paper finishes with conclusions and related ideas for future work.

AB - This paper identifies, by means of video and Kinect data, a set of predictors that estimate the presentation skills of 448 individual students. Two evaluation criteria were predicted: eye contact and posture and body language. Machine-learning evaluations resulted in models that predicted the perfor- mance level (good or poor) of the presenters with 68% and 63% of correctly classified instances, for eye contact and postures and body language criteria, respectively. Furthermore, the results suggest that certain features, such as arms movement and smoothness, provide high significance on predicting the level of development for presentation skills. The paper finishes with conclusions and related ideas for future work.

KW - Multimodal

KW - Presentation skills

KW - Video features

UR - http://www.scopus.com/inward/record.url?scp=84919346826&partnerID=8YFLogxK

U2 - 10.1145/2666633.2666641

DO - 10.1145/2666633.2666641

M3 - Conference Paper

AN - SCOPUS:84919346826

SP - 53

EP - 60

BT - MLA 2014 - Proceedings of the 2014 ACM Multimodal Learning Analytics Workshop and Grand Challenge, Co-located with ICMI 2014

PB - Association for Computing Machinery (ACM)

T2 - Multimodal Learning Analytics Workshop and Grand Challenges 2014

Y2 - 12 November 2014 through 12 November 2014

ER -

Presentation skills estimation based on video and kinect data analysis

Abstract

Workshop

Keywords

Access to Document

Other files and links

Cite this