TY - GEN
T1 - The eye as the window of the language ability
T2 - 13th International Conference on Document Analysis and Recognition, ICDAR 2015
AU - Yoshimura, Kazuyo
AU - Kise, Koichi
AU - Kunze, Kai
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/11/20
Y1 - 2015/11/20
N2 - Reading-life log is a research field of analyzing our activities of reading documents to know more about readers and documents. In this paper we propose an implementation of reading-life log which is to estimate the English language skill by analyzing the activities of reading English documents. As input for the analysis, we employ eye movement information, because we consider the eye movement of skillful readers is far different from that of novices. From the experiments, we have found that the following two features are informative: (1) the sum of fixation duration, and (2) the sum of the velocity of saccades. By using these features the proposed method is to estimate the class of English skill from among low, middle and high, which are defined based on the scores of English standardized test called TOEIC. From the experimental results with 11 subjects and 10 documents, we have been successful to estimate the class with the accuracy of 90.9%.
AB - Reading-life log is a research field of analyzing our activities of reading documents to know more about readers and documents. In this paper we propose an implementation of reading-life log which is to estimate the English language skill by analyzing the activities of reading English documents. As input for the analysis, we employ eye movement information, because we consider the eye movement of skillful readers is far different from that of novices. From the experiments, we have found that the following two features are informative: (1) the sum of fixation duration, and (2) the sum of the velocity of saccades. By using these features the proposed method is to estimate the class of English skill from among low, middle and high, which are defined based on the scores of English standardized test called TOEIC. From the experimental results with 11 subjects and 10 documents, we have been successful to estimate the class with the accuracy of 90.9%.
UR - http://www.scopus.com/inward/record.url?scp=84962522854&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84962522854&partnerID=8YFLogxK
U2 - 10.1109/ICDAR.2015.7333762
DO - 10.1109/ICDAR.2015.7333762
M3 - Conference contribution
AN - SCOPUS:84962522854
T3 - Proceedings of the International Conference on Document Analysis and Recognition, ICDAR
SP - 251
EP - 255
BT - 13th IAPR International Conference on Document Analysis and Recognition, ICDAR 2015 - Conference Proceedings
PB - IEEE Computer Society
Y2 - 23 August 2015 through 26 August 2015
ER -