Abstract
This study investigates a new approach to automatically assessing essay quality that combines traditional approaches based on assessing textual features with new approaches that measure student attributes such as demographic information, standardized test scores, and survey results. The results demonstrate that combining both text features and student attributes leads to essay scoring models that are on par with state-of-the-art scoring models. Such findings expand our knowledge of textual and nontextual features that are predictive of writing success.
Original language | English (US) |
---|---|
Title of host publication | ACM International Conference Proceeding Series |
Publisher | Association for Computing Machinery |
Pages | 203-207 |
Number of pages | 5 |
Volume | 16-20-March-2015 |
ISBN (Print) | 9781450334174 |
DOIs | |
State | Published - Mar 16 2015 |
Event | 5th International Conference on Learning Analytics and Knowledge, LAK 2015 - Poughkeepsie, United States Duration: Mar 16 2015 → Mar 20 2015 |
Other
Other | 5th International Conference on Learning Analytics and Knowledge, LAK 2015 |
---|---|
Country | United States |
City | Poughkeepsie |
Period | 3/16/15 → 3/20/15 |
Fingerprint
Keywords
- Automatic essay scoring
- Corpus linguistics
- Data mining
- Individual differences
- Intelligent tutoring systems
- Natural language processing
ASJC Scopus subject areas
- Human-Computer Interaction
- Computer Networks and Communications
- Computer Vision and Pattern Recognition
- Software
Cite this
Pssst⋯ Textual features⋯ There is more to automatic essay scoring than just you! / Crossley, Scott; Allen, Laura K.; McNamara, Danielle; Snow, Erica L.
ACM International Conference Proceeding Series. Vol. 16-20-March-2015 Association for Computing Machinery, 2015. p. 203-207.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Pssst⋯ Textual features⋯ There is more to automatic essay scoring than just you!
AU - Crossley, Scott
AU - Allen, Laura K.
AU - McNamara, Danielle
AU - Snow, Erica L.
PY - 2015/3/16
Y1 - 2015/3/16
N2 - This study investigates a new approach to automatically assessing essay quality that combines traditional approaches based on assessing textual features with new approaches that measure student attributes such as demographic information, standardized test scores, and survey results. The results demonstrate that combining both text features and student attributes leads to essay scoring models that are on par with state-of-the-art scoring models. Such findings expand our knowledge of textual and nontextual features that are predictive of writing success.
AB - This study investigates a new approach to automatically assessing essay quality that combines traditional approaches based on assessing textual features with new approaches that measure student attributes such as demographic information, standardized test scores, and survey results. The results demonstrate that combining both text features and student attributes leads to essay scoring models that are on par with state-of-the-art scoring models. Such findings expand our knowledge of textual and nontextual features that are predictive of writing success.
KW - Automatic essay scoring
KW - Corpus linguistics
KW - Data mining
KW - Individual differences
KW - Intelligent tutoring systems
KW - Natural language processing
UR - http://www.scopus.com/inward/record.url?scp=84955561979&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84955561979&partnerID=8YFLogxK
U2 - 10.1145/2723576.2723595
DO - 10.1145/2723576.2723595
M3 - Conference contribution
AN - SCOPUS:84955561979
SN - 9781450334174
VL - 16-20-March-2015
SP - 203
EP - 207
BT - ACM International Conference Proceeding Series
PB - Association for Computing Machinery
ER -