Affect Detection: An Interdisciplinary Review of Models, Methods, and Their Applications

Calvo, Rafael A.; D’Mello, Sidney K.

doi:10.1109/t-affc.2010.1

Cited by 1,387 publications

(790 citation statements)

References 174 publications

Supporting

Mentioning

728

Contrasting

Unclassified

Order By: Relevance

“…To begin with, emotions are difficult to define from a psychological point of view [33]. In fact, emotions are ill-defined, possibly indeterminate, and they exhibit fuzzy boundaries that cannot be directly measured [12]. There are ongoing debates about how many emotion categories exist [33].…”

Section: Introductionmentioning

confidence: 99%

Speaker-independent emotion recognition exploiting a psychologically-inspired binary cascade classification schema

Kotti

Paternò

2012

Int J Speech Technol

View full text Add to dashboard Cite

In this paper, a psychologically-inspired binary cascade classification schema is proposed for speech emotion recognition. Performance is enhanced because commonly confused pairs of emotions are distinguishable from one another. Extracted features are related to statistics of pitch, formants, and energy contours, as well as spectrum, cepstrum, perceptual and temporal features, autocorrelation, MPEG-7 descriptors, Fujisaki's model parameters, voice quality, jitter, and shimmer. Selected features are fed as input to K nearest neighborhood classifier and to support vector machines. Two kernels are tested for the latter: linear and Gaussian radial basis function. The recently proposed speaker-independent experimental protocol is tested on the Berlin emotional speech database for each gender separately. The best emotion recognition accuracy, achieved by support vector machines with linear kernel, equals 87.7%, outperforming state-of-the-art approaches. Statistical analysis is first carried out with respect to the classifiers' error rates and then to evaluate the information expressed by the classifiers' confusion matrices.

show abstract

Section: Introductionmentioning

confidence: 99%

Speaker-independent emotion recognition exploiting a psychologically-inspired binary cascade classification schema

Kotti

Paternò

2012

Int J Speech Technol

View full text Add to dashboard Cite

show abstract

“…Part-of-Speech (POS) features: Similar to [32], we used features to model the occurrence of verbs, adverbs, nouns and adjectives in a document. Part-of-speech tagging on non-social media data sets is done using the stanford POS tagger 3 , whilst Twitter NLP tool [40] from Carnegie Mellon University was used for tagging social media data sets .…”

Section: Baseline Emotion Featuresmentioning

confidence: 99%

“…Given that there is unprecedented access to emotion-rich content through tweets, blogs and discussion posts there is a great opportunity and need to build automatic tools, in order to understand the emotions of the users. Emotion classification is among the most widely studied problems in emotion analysis of text, where supervised machine learning methods are leveraged to classify text documents [3,4] into emotion classes, induced from emotion theories proposed in psychology by Ekman [5], Parrot [6] and Plutchik [7]. Among the two approaches for emotion modelling [4], one on discrete emotions and another using the continuum approach, this work builds upon the former.…”

Section: Introductionmentioning

confidence: 99%

Lexicon based feature extraction for emotion text classification

Bandhakavi

Wiratunga

Deepak

et al. 2017

Pattern Recognition Letters

131

View full text Add to dashboard Cite

“…Although reasonably effective models can be constructed using physical sensors such as cameras and posture sensors (see Calvo and D'Mello [2010] for review) these sensors can be challenging to deploy at scale in schools, due to issues of cost and breakage in these settings. However, multiyear efforts to understand and engineer the types of features associated with engagement and affect in interaction data have begun to produce automated detectors that are reliable and effective for these situations.…”

Section: The Difference Between Generic Model Parameters and The Inmentioning

confidence: 99%

New Potentials for Data‐Driven Intelligent Tutoring System Development and Optimization

et al. 2013

View full text Add to dashboard Cite

Increasing widespread use of educational technologies is producing vast amounts of data. Such data can be used to help advance our understanding of student learning and enable more intelligent, interactive, engaging, and effective education. In this article, we discuss the status and prospects of this new and powerful opportunity for data-driven development and optimization of educational technologies, focusing on intelligent tutoring systems We provide examples of use of a variety of techniques to develop or optimize the select, evaluate, suggest, and update functions of intelligent tutors, including probabilistic grammar learning, rule induction, Markov decision process, classification, and integrations of symbolic search and statistical inference.

show abstract

Affect Detection: An Interdisciplinary Review of Models, Methods, and Their Applications

Cited by 1,387 publications

References 174 publications

Speaker-independent emotion recognition exploiting a psychologically-inspired binary cascade classification schema

Speaker-independent emotion recognition exploiting a psychologically-inspired binary cascade classification schema

Lexicon based feature extraction for emotion text classification

New Potentials for Data‐Driven Intelligent Tutoring System Development and Optimization

Contact Info

Product

Resources

About