Interact: web and android-based backchannel system to aggregate student feedback

Goh Si Hao, Soumyadeb Chowdhury, Sam Loh, Junqi Zou

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents, 'Interact', an interactive backchannel system providing an array of features to both the students and instructors. It allows the students to post comments, ask questions, and rate their understanding of various concepts (prepopulated by the instructor), taught in a lecture session. Additionally, the system employs text analytics using Latent Dirichlet allocation (LDA), to extract topics from the comments, and aggregate sentiments for each topic using AFINN-165 wordlist. The instructors can view: (1) top-ranked 'm' topics discussed in 'n' lectures; (2) sentiment trends for 'm' topics, and 'n' lectures, including positive and negative words; (3) popular questions asked in 'n' lectures. A user-study was conducted with 40 students and 10 academics were interviewed to understand their perception towards the system. Additionally, a crowdsource study examined the effectiveness of aggregation techniques. We believe that Interact will help to improve teaching and develop effective learning, with the aid of automatic processing, summarization and visualization of student feedback obtained through comments, questions and rating concepts.

Original languageEnglish
Title of host publicationOZCHI '17 Proceedings of the 29th Australian Conference on Computer-Human Interaction
PublisherACM
Pages508-512
Number of pages5
ISBN (Electronic)9781450353793
DOIs
Publication statusPublished - 28 Nov 2017
Event29th Australian Computer-Human Interaction Conference, OzCHI 2017 - Brisbane, Australia
Duration: 28 Nov 20171 Dec 2017

Conference

Conference29th Australian Computer-Human Interaction Conference, OzCHI 2017
CountryAustralia
CityBrisbane
Period28/11/171/12/17

Fingerprint

Students
Feedback
Teaching
Agglomeration
Visualization
Processing

Keywords

  • Backchannel
  • Sentiment
  • User-study
  • Visualization

Cite this

Hao, G. S., Chowdhury, S., Loh, S., & Zou, J. (2017). Interact: web and android-based backchannel system to aggregate student feedback. In OZCHI '17 Proceedings of the 29th Australian Conference on Computer-Human Interaction (pp. 508-512). ACM. https://doi.org/10.1145/3152771.3156167
Hao, Goh Si ; Chowdhury, Soumyadeb ; Loh, Sam ; Zou, Junqi. / Interact: web and android-based backchannel system to aggregate student feedback. OZCHI '17 Proceedings of the 29th Australian Conference on Computer-Human Interaction. ACM, 2017. pp. 508-512
@inproceedings{e3ecc6cdc0344441959f77409affa317,
title = "Interact: web and android-based backchannel system to aggregate student feedback",
abstract = "This paper presents, 'Interact', an interactive backchannel system providing an array of features to both the students and instructors. It allows the students to post comments, ask questions, and rate their understanding of various concepts (prepopulated by the instructor), taught in a lecture session. Additionally, the system employs text analytics using Latent Dirichlet allocation (LDA), to extract topics from the comments, and aggregate sentiments for each topic using AFINN-165 wordlist. The instructors can view: (1) top-ranked 'm' topics discussed in 'n' lectures; (2) sentiment trends for 'm' topics, and 'n' lectures, including positive and negative words; (3) popular questions asked in 'n' lectures. A user-study was conducted with 40 students and 10 academics were interviewed to understand their perception towards the system. Additionally, a crowdsource study examined the effectiveness of aggregation techniques. We believe that Interact will help to improve teaching and develop effective learning, with the aid of automatic processing, summarization and visualization of student feedback obtained through comments, questions and rating concepts.",
keywords = "Backchannel, Sentiment, User-study, Visualization",
author = "Hao, {Goh Si} and Soumyadeb Chowdhury and Sam Loh and Junqi Zou",
year = "2017",
month = "11",
day = "28",
doi = "10.1145/3152771.3156167",
language = "English",
pages = "508--512",
booktitle = "OZCHI '17 Proceedings of the 29th Australian Conference on Computer-Human Interaction",
publisher = "ACM",
address = "United States",

}

Hao, GS, Chowdhury, S, Loh, S & Zou, J 2017, Interact: web and android-based backchannel system to aggregate student feedback. in OZCHI '17 Proceedings of the 29th Australian Conference on Computer-Human Interaction. ACM, pp. 508-512, 29th Australian Computer-Human Interaction Conference, OzCHI 2017, Brisbane, Australia, 28/11/17. https://doi.org/10.1145/3152771.3156167

Interact: web and android-based backchannel system to aggregate student feedback. / Hao, Goh Si; Chowdhury, Soumyadeb; Loh, Sam; Zou, Junqi.

OZCHI '17 Proceedings of the 29th Australian Conference on Computer-Human Interaction. ACM, 2017. p. 508-512.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Interact: web and android-based backchannel system to aggregate student feedback

AU - Hao, Goh Si

AU - Chowdhury, Soumyadeb

AU - Loh, Sam

AU - Zou, Junqi

PY - 2017/11/28

Y1 - 2017/11/28

N2 - This paper presents, 'Interact', an interactive backchannel system providing an array of features to both the students and instructors. It allows the students to post comments, ask questions, and rate their understanding of various concepts (prepopulated by the instructor), taught in a lecture session. Additionally, the system employs text analytics using Latent Dirichlet allocation (LDA), to extract topics from the comments, and aggregate sentiments for each topic using AFINN-165 wordlist. The instructors can view: (1) top-ranked 'm' topics discussed in 'n' lectures; (2) sentiment trends for 'm' topics, and 'n' lectures, including positive and negative words; (3) popular questions asked in 'n' lectures. A user-study was conducted with 40 students and 10 academics were interviewed to understand their perception towards the system. Additionally, a crowdsource study examined the effectiveness of aggregation techniques. We believe that Interact will help to improve teaching and develop effective learning, with the aid of automatic processing, summarization and visualization of student feedback obtained through comments, questions and rating concepts.

AB - This paper presents, 'Interact', an interactive backchannel system providing an array of features to both the students and instructors. It allows the students to post comments, ask questions, and rate their understanding of various concepts (prepopulated by the instructor), taught in a lecture session. Additionally, the system employs text analytics using Latent Dirichlet allocation (LDA), to extract topics from the comments, and aggregate sentiments for each topic using AFINN-165 wordlist. The instructors can view: (1) top-ranked 'm' topics discussed in 'n' lectures; (2) sentiment trends for 'm' topics, and 'n' lectures, including positive and negative words; (3) popular questions asked in 'n' lectures. A user-study was conducted with 40 students and 10 academics were interviewed to understand their perception towards the system. Additionally, a crowdsource study examined the effectiveness of aggregation techniques. We believe that Interact will help to improve teaching and develop effective learning, with the aid of automatic processing, summarization and visualization of student feedback obtained through comments, questions and rating concepts.

KW - Backchannel

KW - Sentiment

KW - User-study

KW - Visualization

UR - http://www.scopus.com/inward/record.url?scp=85044220344&partnerID=8YFLogxK

UR - https://dl.acm.org/citation.cfm?doid=3152771.3156167

U2 - 10.1145/3152771.3156167

DO - 10.1145/3152771.3156167

M3 - Conference contribution

SP - 508

EP - 512

BT - OZCHI '17 Proceedings of the 29th Australian Conference on Computer-Human Interaction

PB - ACM

ER -

Hao GS, Chowdhury S, Loh S, Zou J. Interact: web and android-based backchannel system to aggregate student feedback. In OZCHI '17 Proceedings of the 29th Australian Conference on Computer-Human Interaction. ACM. 2017. p. 508-512 https://doi.org/10.1145/3152771.3156167