• Corpus ID: 219303023

Improving Sentiment Analysis with Biofeedback Data

@inproceedings{Schlr2020ImprovingSA,
  title={Improving Sentiment Analysis with Biofeedback Data},
  author={Daniel Schl{\"o}r and Albin Zehe and Konstantin Kobs and Blerta Veseli and Franziska Westermeier and Larissa Br{\"u}bach and Daniel Roth and Marc Erich Latoschik and Andreas Hotho},
  booktitle={ONION},
  year={2020}
}
Humans frequently are able to read and interpret emotions of others by directly taking verbal and non-verbal signals in human-to-human communication into account or to infer or even experience emotions from mediated stories. For computers, however, emotion recognition is a complex problem: Thoughts and feelings are the roots of many behavioural responses and they are deeply entangled with neurophysiological changes within humans. As such, emotions are very subjective, often are expressed in a… 

Figures and Tables from this paper

Sentiment Analysis: Using Detrended Fluctation Analysis of EEG Signals in Natural Reading

It is shown how Detrended Fluctuation Analysis (DFA), an extension to chaotic systems fluctuation analysis, can be used to identify differences and changes in human EEG for reading texts with different sentiments.

References

SHOWING 1-10 OF 33 REFERENCES

Using Brain Data for Sentiment Analysis

The lexical polarity extracted from brain data was exploited for the prediction of the valence of 12 sentences taken from the SemEval-2007 shared task, and compared it against existing lexical resources.

Classification of human emotions from EEG signals using SVM and LDA Classifiers

The present work employs Independent Component Analysis and Machine Learning techniques to classify EEG signals into seven different emotions and is able to recognize seven emotions using the two algorithms, SVM and LDA with an average overall accuracy of 74.13% and 66.50% respectively.

Human Emotion Classification from Brain EEG Signal Using Multimodal Approach of Classifier

EEG-based emotion recognition models for three emotions: positive, neutral and negative are developed and Gamma band is selected as it relates to emotional states more closely than other frequency bands.

Emotion recognition using brain activity

This system was designed using prior knowledge from other research, and is meant to assess the quality of emotion recognition using EEG signals in practice, and found that the EEG signals contained enough information to separate five different classes on both the valence and arousal dimension.

EEG-Based Emotion Recognition in Music Listening

This study applied machine-learning algorithms to categorize EEG dynamics according to subject self-reported emotional states during music listening to identify 30 subject-independent features that were most relevant to emotional processing across subjects and explored the feasibility of using fewer electrodes to characterize the EEG dynamics duringMusic listening.

Consumer Grade Brain Sensing for Emotion Recognition

OpenBCI is evaluated by first comparing its performance to research grade EEG system, employing the same algorithms that were applied on benchmark datasets and a novel method to facilitate the selection of audio-visual stimuli of high/low valence and arousal is proposed for emotion classification.

Affective Computing

Key issues in affective computing, " computing that relates to, arises from, or influences emotions", are presented and new applications are presented for computer-assisted learning, perceptual information retrieval, arts and entertainment, and human health and interaction.

MixedEmotions: An Open-Source Toolbox for Multimodal Emotion Analysis

The MixedEmotions Toolbox leverages the need for functionalities for recognizing emotions from user-generated media content in automated systems by providing tools for text, audio, video, and linked data processing within an easily integrable plug-and-play platform.

Resource Creation Towards Automated Sentiment Analysis in Telugu (a low resource language) and Integrating Multiple Domain Sources to Enhance Sentiment Prediction

This paper created corpora "Sentiraama" for different domains like movie reviews, song lyrics, product reviews and book reviews in Telugu language with the text written inTelugu script, and built sentiment model using data samples from multiple domains and tested the performance of the models based on their classification.

Differential entropy feature for EEG-based emotion classification

A new effective EEG feature named differential entropy is proposed to represent the characteristics associated with emotional states and its combination on symmetrical electrodes and it is confirmed that EEG signals on frequency band Gamma relates to emotional states more closely than other frequency bands.