Predicting Emotional Reaction in Social Networks

Clos, Jérémie; Bandhakavi, Anil; Wiratunga, Nirmalie; Cabanac, Guillaume

doi:10.1007/978-3-319-56608-5_44

Cited by 11 publications

(8 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another explanation could be a gender bias in the emotion detector. Vokaturi's training databases 3 are the Berlin Database of Emotional Speech or Emo-DB 4 [2], which contains five female and five male speakers, and SAVEE 5 , which has voice samples of four males. This raises the question whether the training databases for emotion detection have to be gender-balanced.…”

Section: Discussion and Future Workmentioning

confidence: 99%

“…Li et al [5] worked on emotional reaction by focusing on the feelings of the user and presented the 'EmoElicitor' model to elicit the particular emotions of users. Clos et al [3] tried to predict the emotional reaction of readers of social network posts. Other researchers concluded that their approach outperforms other approaches they took as a baseline, e.g., estimating emotion from text by using 'EmoLex' [7].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

How Should Voice Assistants Deal With Users' Emotions?

Ma¹,

Drewes²,

Butz³

2022

Preprint

View full text Add to dashboard Cite

There is a growing body of research in HCI on detecting the users' emotions. Once it is possible to detect users' emotions reliably, the next question is how an emotion-aware interface should react to the detected emotion. In a first step, we tried to find out how humans deal with negative emotions of an avatar. The hope behind this approach was to identify human strategies, which we can then mimic in an emotion-aware voice assistant. We present a user study in which participants were confronted with an angry, sad, or frightened avatar. Their task was to make the avatar happy by talking to it. We recorded the voice signal and analyzed it. The results show that users predominantly reacted with neutral emotion. However, we also found gender differences, which opens a range of questions.CCS Concepts: • Human-centered computing → Natural language interfaces.

show abstract

Section: Discussion and Future Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

How Should Voice Assistants Deal With Users' Emotions?

Ma¹,

Drewes²,

Butz³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In contrast, our goal is to address the breadth of content on social media. There are works which use Facebook reactions as a proxy for affective response, but these are constrained by the pre-defined set of reactions (Clos et al, 2017;Raad et al, 2018;Pool and Nissim, 2016;Graziani et al, 2019;Krebs et al, 2017). The work described in and Bao et al (2012) attempts to associate emotions with topics, but a single topic can have a large variety of affective responses when seen on social media, and therefore their model does not apply to our case.…”

Section: Affective Response Detectionmentioning

confidence: 99%

The CARE Dataset for Affective Response Detection

Jane¹,

Halevy²

2022

Preprint

View full text Add to dashboard Cite

Social media plays an increasing role in our communication with friends and family, and our consumption of information and entertainment. Hence, to design effective ranking functions for posts on social media, it would be useful to predict the affective response to a post (e.g., whether the user is likely to be humored, inspired, angered, informed). Similar to work on emotion recognition (which focuses on the affect of the publisher of the post), the traditional approach to recognizing affective response would involve an expensive investment in human annotation of training data.We introduce CARE db , a dataset of 230k social media posts annotated according to 7 affective responses using the Common Affective Response Expression (CARE) method. The CARE method is a means of leveraging the signal that is present in comments that are posted in response to a post, providing high-precision evidence about the affective response of the readers to the post without human annotation. Unlike human annotation, the annotation process we describe here can be iterated upon to expand the coverage of the method, particularly for new affective responses. We present experiments that demonstrate that the CARE annotations compare favorably with crowdsourced annotations. Finally, we use CARE db to train competitive BERT-based models for predicting affective response as well as emotion detection, demonstrating the utility of the dataset for related tasks.

show abstract

“…Lexicons are linguistic tools for the automated analysis of text. Their most notorious uses are classification and feature extraction [5,2]. They can take many forms, the most common of which is a simple list of terms associated to a certain class of interest.…”

Section: Lexicon-based Classificationmentioning

confidence: 99%

“…• The AYI dataset was collected from Amazon 3 , Yelp 4 and IMDB 5 and was built from individual sentences from product, location and movie reviews (respectively), labeled with a binary positive/negative judgment.…”

Section: Datasetsmentioning

confidence: 99%