Aspect-Based Extraction and Analysis of Affective Knowledge from Social Media Streams

Weichselbraun, Albert; Gindl, Stefan; Fischer, Fabian; Vakulenko, Svitlana; Scharl, Arno

doi:10.1109/mis.2017.57

Cited by 44 publications

(16 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This approach improves the prediction accuracies in speaker independent sentiment intensity analysis. Multiple other recent studies under the topic of unimodal and multimodal sentiment or emotion analysis are reported in [30][31][32][33][34][35][36][37][38][39][40][41].…”

Section: Background and Literature Review On Multimodal Emotion Rmentioning

confidence: 99%

Cross-Subject Multimodal Emotion Recognition Based on Hybrid Fusion

2020

View full text Add to dashboard Cite

Multimodal emotion recognition has gained traction in affective computing research community to overcome the limitations posed by the processing a single form of data and to increase recognition robustness. In this study, a novel emotion recognition system is introduced, which is based on multiple modalities including facial expressions, galvanic skin response (GSR) and electroencephalogram (EEG). This method follows a hybrid fusion strategy and yields a maximum one-subject-out accuracy of 81.2% and a mean accuracy of 74.2% on our bespoke multimodal emotion dataset (LUMED-2) for 3 emotion classes: sad, neutral and happy. Similarly, our approach yields a maximum one-subject-out accuracy of 91.5% and a mean accuracy of 53.8% on the Database for Emotion Analysis using Physiological Signals (DEAP) for varying numbers of emotion classes, 4 in average, including angry, disgust, afraid, happy, neutral, sad and surprised. The presented model is particularly useful in determining the correct emotional state in the case of natural deceptive facial expressions. In terms of emotion recognition accuracy, this study is superior to, or on par with, the reference subject-independent multimodal emotion recognition studies introduced in the literature.

show abstract

Section: Background and Literature Review On Multimodal Emotion Rmentioning

confidence: 99%

Cross-Subject Multimodal Emotion Recognition Based on Hybrid Fusion

2020

View full text Add to dashboard Cite

show abstract

“…In particular, emotional expressions (e.g., speech and text) could be recognized as affective dimensions, which are modeled by the hourglass of emotions (Cambria, Livingstone, & Hussain, 2012). In addition novel techniques, involved fuzzy linguistic modeling, aspect‐based extraction, flow of emotions modeling and others, have proposed to identify an affective state (i.e., emotions) based on the rich text of social media (Brenga, Celotto, Loia, & Senatore, 2015a; Maharjan, Kar, Montes, González, & Solorio, 2018; Weichselbraun, Gindl, Fischer, Vakulenko, & Scharl, 2017). In this regard, social media data have boosted the utilization of emotional texts to understand human behaviors, observations, opinions, and so on.…”

Section: Related Workmentioning

confidence: 99%

Discovering underlying sensations of human emotions based on social media

Lee

Jatowt

Kim

2020

Asso for Info Science & Tech

View full text Add to dashboard Cite

Analyzing social media has become a common way for capturing and understanding people's opinions, sentiments, interests, and reactions to ongoing events. Social media has thus become a rich and real‐time source for various kinds of public opinion and sentiment studies. According to psychology and neuroscience, human emotions are known to be strongly dependent on sensory perceptions. Although sensation is the most fundamental antecedent of human emotions, prior works have not looked into their relation to emotions based on social media texts. In this paper, we report the results of our study on sensation effects that underlie human emotions as revealed in social media. We focus on the key five types of sensations: sight, hearing, touch, smell, and taste. We first establish a correlation between emotion and sensation in terms of linguistic expressions. Then, in the second part of the paper, we define novel features useful for extracting sensation information from social media. Finally, we design a method to classify texts into ones associated with different types of sensations. The sensation dataset resulting from this research is opened to the public to foster further studies.

show abstract

“…2 Zusätzlich ermöglicht das Tool auch eine Schlagwortsuche über die Datenbank aller Twitter-UserInnen, um die öffentliche Meinung zu sicherheitsrelevanten Themen abzubilden. (Weichselbraun et al 2017(Weichselbraun et al , 2014(Weichselbraun et al , 2013. Die Daten für den Vergleich wurden am 11.07.2017 aus dem Weblyzard extrahiert.…”

Section: Operationalisierung Des Modells Mittels Schlagwörternunclassified

Lässt sich das Sicherheitsgefühl der Bevölkerung automatisiert erfassen?

Aschauer

Seymer

Weichbold

et al. 2019

Österreich Z Soziol

View full text Add to dashboard Cite

Zusammenfassung Seit Oktober 2015 sind wir als wissenschaftlicher Partner an zwei von der FFG geförderten Projekten im Sicherheitsforschungsprogramm KIRAS beteiligt. Im Zuge des ersten Projekts (Laufzeit bis Oktober 2016) wurde in Kooperation mit Unternehmensberatern und einer IT-Firma die Online-Plattform Foresight-Cockpit entwickelt. Diese hat das Ziel, die österreichischen Ministerien in die Lage zu versetzen, kollaborativ sowie ressortübergreifend frühzeitig auf unerwartete Trendbewegungen und Zukunftsszenarien im Bereich Sicherheit aufmerksam zu werden, sodass dauerhaft die Qualität des Risiko-und Krisenmanagements gesteigert werden kann. Im aktuellen Projekt (Laufzeit bis Oktober 2017) wurde eine softwarebasierte Lösung (genannt "Weblyzard") zur Analyse von Nachrichtenquellen und Social-Media-Daten in das bestehende Tool integriert, um den künftigen NutzerInnen der Plattform die Analyse sicherheitspolitischer Lageperzeptionen und Stimmungslagen in der Bevölkerung zu erleichtern. Die vorliegende Fallstudie soll primär die Möglichkeiten und Grenzen von Big-Data-Analysen auf Basis von Medienquellen im Vergleich zu klassischen quantitativen Inhaltsanalysen im Kontext einer Evaluationsstudie aufzeigen. Insofern entschieden wir, mit einer konventionellen Inhaltsanalyse auf Basis von zwei reichweiten

show abstract

Aspect-Based Extraction and Analysis of Affective Knowledge from Social Media Streams

Cited by 44 publications

References 22 publications

Cross-Subject Multimodal Emotion Recognition Based on Hybrid Fusion

Cross-Subject Multimodal Emotion Recognition Based on Hybrid Fusion

Discovering underlying sensations of human emotions based on social media

Lässt sich das Sicherheitsgefühl der Bevölkerung automatisiert erfassen?

Contact Info

Product

Resources

About