數學學習環境中學生情緒之標記與分析

Annotation and Analysis of Students’ Emotions in Mathematics Learning

梁壽芳(Shou-Fang Liang)

指導教授 ： 禹良治

元智大學/資訊學院/資訊管理學系/碩士(2012年)

摘要

情緒在數位學習環境扮演一個重要的角色，並且可能影響學習者的學習表現。因此，如何利用機器學習演算法自動判斷學習者的情緒變成為一個熱門的研究主題，為提供訓練語料，收集並分析學生在學習環境中所發生的情緒類別便是相當重要的步驟之一。本研究以數學學習為例，收集學生情緒文字語料並標記情緒類別，最後分析各種情緒類別之比例、不同情緒的語言特徵，標記一致性等，提供未來實作自動情緒辨識之參考。

關鍵字

語料標記與分析 ； 情緒 ； 數位學習

並列摘要

Emotions play an important role in e-learning environments, and may affect learning outcomes. Therefore, automatic emotion recognition of student’s emotions using machine learning algorithms has become an emerging research topic. To accomplish this goal, the first step is to collect a corpus of labeled emotions, and analyze the emotion types in the corpus. This study collects a text corpus of emotion sentences in mathematics learning. Each sentence is then annotated to provide analysis results such as the linguistic features, proportions, annotator agreements, and annotation accuracy for different emotions.

並列關鍵字

Corpus annotation and analysis ； Emotion ； E-learning

參考文獻

[1] D’Mello, S., Graesser, A. & Picard, R. W. (2007). Toward an Affect-Sensitive AutoTutor. Intelligent Systems, 22(4), 53-61.

[5] Cook, N. D., Fujisawa, T. X. & Takami, K. (2006). Evaluation of the Affective Valence of Speech Using Pitch Substructure. IEEE Trans. Audio, Speech, and Language Processing, 14(1), 142-151.

[6] I. Luengo, E. Navas, and I. Hernaez. 2010. Feature Analysis and Evaluation for Automatic Emotion Identification in Speech. IEEE Trans. Multimedia, 12(6), 490-501.

[7] Litman, D. J. & Silliman, S. (2004). ITSPOKE: An Intelligent Tutoring Spoken Dialogue System, Proceedings of HLT/NAACL'04, Boston, MA.

[8] Horiguchi, Y., Kojima K. & Matsui, T. (2009). A Study for Exploration of Relationships between Behaviors and Mental States of Learners for an Automatic Estimation System, Proceedings of ICCE’09 (pp. 173-175), Hong Kong, China.