An SVM Plait for Improving Affect Recognition in Intelligent Tutoring Systems

Janning, Ruth; Schatten, Carlotta; Schmidt-Thieme, Lars; Backfried, Gerhard; Pfannerer, Norbert

doi:10.1109/ictai.2014.38

Cited by 4 publications

(10 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The goal is to investigate which classification model performs best for the log-file features and if the above mentioned approach for performance improvement also works on classification models other than SVMs. Furthermore, in opposite to Janning et al (2014e) where we solved a binary classification problem, in this work we address a multi-class classification problem and show that the approach of Janning et al (2014e) also works for multi-class classification.…”

Section: Introductionmentioning

confidence: 94%

“…Acoustic-prosodic features as well as lexical features are used in the context of emotion prediction in Forbes- , Litman and Forbes-Riley (2004) and Ai et al (2006). Low-level features are used in the literature for instance for expert identification, as in Worsley and Blikstein (2011), Morency et al (2013) and Luz (2013), or for emotion and affect recognition as in Moore et al (2014) and Janning et al (2014e), or for humour recognition as in Purandare and Litman (2006). The advantage of using low-level features like disfluencies is that instead of a full transcription or speech recognition approach only for instance a pause identification has to be applied before computing the features.…”

Section: Related Workmentioning

confidence: 99%

“…speech pauses) or articulation features (see e.g. Schuller et al (2011) andJanning et al (2014e)) can be distinguished. If linguistics features are used, a transcription or speech recognition process has to be applied to the speech input before affect recognition can be conducted.…”

Section: Related Workmentioning

confidence: 99%

“…Hence, the question arises, is there a way to improve the classification performance? Janning et al (2014e) presented an approach for improving the affect recognition performance of SVMs applied to features extracted from speech. In this work we will further investigate this approach on the one hand by applying it to log-file features instead of speech features and on the other hand by applying the approach of Janning et al (2014e) also to other classification models.…”

Section: Introductionmentioning

confidence: 99%

“…Janning et al (2014e) presented an approach for improving the affect recognition performance of SVMs applied to features extracted from speech. In this work we will further investigate this approach on the one hand by applying it to log-file features instead of speech features and on the other hand by applying the approach of Janning et al (2014e) also to other classification models. The goal is to investigate which classification model performs best for the log-file features and if the above mentioned approach for performance improvement also works on classification models other than SVMs.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Perceived Task-Difficulty Recognition from Log-file Information for the Use in Adaptive Intelligent Tutoring Systems

Janning

Schatten

Schmidt-Thieme

2016

Int J Artif Intell Educ

Self Cite

View full text Add to dashboard Cite

Recognising students' emotion, affect or cognition is a relatively young field and still a challenging task in the area of intelligent tutoring systems. There are several ways to use the output of these recognition tasks within the system. The approach most often mentioned in the literature is using it for giving feedback to the students. The features used for that approach can be high-level features like linguistics features which are words related to emotions or affects, taken e.g. from written or spoken inputs, or low-level features like log-file features which are created from information contained in the log-files. In this work we aim at supporting task sequencing by perceived task-difficulty recognition on low-level features easily extracted from the log-file. We analyse these features by statistical tests showing that there are statistically significant feature combinations and hence the presented features are able to describe students' perceived task-difficulty in intelligent tutoring systems. Furthermore, we apply different classification methods to the log-file features for perceived task-difficulty recognition and present a kind of higher ensemble method for improving the classification performance on the features extracted from a real data set. The presented approach outperforms classical ensemble methods and is able to improve the classification performance substantially, enabling a perceived task-difficulty recognition satisfactory enough for employing its output for components of a real system like task independent support or task sequencing.

show abstract

Section: Introductionmentioning

confidence: 94%