Abstract
| Original language | English |
|---|---|
| Title of host publication | ARTIFICIAL INTELLIGENCE - 30th Benelux Conference, BNAIC 2018, Den Bosch November 8-9 2018, Revised Selected Papers |
| Publisher | Springer |
| Pages | 331-340 |
| Number of pages | 10 |
| ISBN (Print) | 9783030319779 |
| Publication status | Published - 2019 |
| Event | 30th Benelux Conference on Artificial Intelligence (BNAIC 2018) - Den Bosch Duration: 8 Nov 2018 → 9 Nov 2018 Conference number: 30th |
Conference
| Conference | 30th Benelux Conference on Artificial Intelligence (BNAIC 2018) |
|---|---|
| Abbreviated title | BNAIC 2018 |
| City | Den Bosch |
| Period | 8/11/18 → 9/11/18 |
Fingerprint
Cite this
}
Challenge Balancing for a Kanji E-Tutoring System. / Winkels, Marysia; Roijers, D.M.; van Someren, Maarten; Yamamoto, Emi; Pronk, Richard; Odijk, Edwin; de Jonge, Maarten.
ARTIFICIAL INTELLIGENCE - 30th Benelux Conference, BNAIC 2018, Den Bosch November 8-9 2018, Revised Selected Papers. Springer, 2019. p. 331-340.Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review
TY - GEN
T1 - Challenge Balancing for a Kanji E-Tutoring System
AU - Winkels, Marysia
AU - Roijers, D.M.
AU - van Someren, Maarten
AU - Yamamoto, Emi
AU - Pronk, Richard
AU - Odijk, Edwin
AU - de Jonge, Maarten
PY - 2019
Y1 - 2019
N2 - In this paper, we investigate the potential of direct challenge balancing in e-tutoring, especially in domains where there are many skills to acquire. As a case study, we create an e-tutoring system for kanji. Our system estimates the perceived challenge level using both the correctness of the answers of the students and implicit feedback, and adapts accordingly. In order to make this estimation we train a classifier on labelled data collected via the same system. We show empirically that the perceived challenge can be estimated well using implicit feedback, and that the adaptive system based on challenge balancing is preferred over a system in which the student selects a difficulty setting, indicating that directchallenge balancing is a promising research direction for e-tutoring.
AB - In this paper, we investigate the potential of direct challenge balancing in e-tutoring, especially in domains where there are many skills to acquire. As a case study, we create an e-tutoring system for kanji. Our system estimates the perceived challenge level using both the correctness of the answers of the students and implicit feedback, and adapts accordingly. In order to make this estimation we train a classifier on labelled data collected via the same system. We show empirically that the perceived challenge can be estimated well using implicit feedback, and that the adaptive system based on challenge balancing is preferred over a system in which the student selects a difficulty setting, indicating that directchallenge balancing is a promising research direction for e-tutoring.
M3 - Conference contribution
SN - 9783030319779
SP - 331
EP - 340
BT - ARTIFICIAL INTELLIGENCE - 30th Benelux Conference, BNAIC 2018, Den Bosch November 8-9 2018, Revised Selected Papers
PB - Springer
ER -