Statistical affect detection in collaborative chat

Brooks, Michael; Kuksenok, Katie; Torkildson, Megan K.; Perry, Daniel; Robinson, John J.; Scott, Taylor Jackson; Anicello, Ona; Zukowski, A. T.; Harris, Paul G.; Aragon, C.

doi:10.1145/2441776.2441813

Cited by 49 publications

(31 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Humans usually express sentiment through multiple modalities such as 'facial expressions', 'voice' including both linguistic expressions and non-linguistic vocalizations and 'body language' [1], hence detecting sentiment using only 'text' is in itself a challenging task. However, natural language text is one of the most prevalent means of communication on E-Commerce and social-media platforms, hence efficient mining of sentiment from blog text is relevant in many contexts [2], [3], [4], [5], [6], [7], [8], [9], [10].…”

Section: Introductionmentioning

confidence: 99%

“…Sentiment mining from text has been applied to a variety of useful and diverse applications in literature such as, understanding the sentiments of a geographically distributed team through their chat logs [2], analyzing the effect of negative opinions expressed in financial media text on potential investors [3], classifying and statistically summarizing the sentiment polarity expressed in online product reviews by customers [4], [5], discerning the emotions of students through sentiment analysis of the dialog between students and computerized tutoring system [6], mining of sentiment orientation from political blogs [7], [8], [9] etc.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Sentiment Mining from Text: A Technical Review

Dalal¹

2017

IJCA

View full text Add to dashboard Cite

Expression of sentiments is an integral aspect of human communication. The prevalence of Internet and social media platforms has facilitated the exchange and storage of large volumes of human communication in the form of natural language text which can be mined for various intelligencebased applications. In order to build computers that can serve humans better, there are ongoing efforts in computer science research to develop machine learning algorithms that can process the textual data and perform sentiment mining tasks such as, 'detecting the presence of emotion in text', 'selecting a model for representing emotion', 'classifying the sentiment polarity of text' and 'measuring the intensity of the expressed sentiment in text'. This paper aims to discuss the challenges posed to the various tasks associated with mining sentiment from text, review the existing methods to address these challenges in contemporary literature and identify important areas for future scope of research in this field.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Sentiment Mining from Text: A Technical Review

Dalal¹

2017

IJCA

View full text Add to dashboard Cite

show abstract

“…Many methods have been introduced by researchers for emotion annotation work. This gives binary labels for the given text (Alm et al, 2005), (Aman and Szpakowicz, 2007;Brooks et al, 2013), (Neviarouskaya et al, 2009), (Bollen et al, 2011), (Summa et al, 2016. only one annotation work exists for providing a real valued score as annotation for a given text (Strapparava and Mihalcea, 2007).…”

Section: Introductionmentioning

confidence: 99%

“…This was a task included in the SemEval-2007 shared task. Many methods devised for automatic emotion classification (Werbos, 1990), (Summa et al, 2016), (Mohammad, 2012), (Bollen et al, 2011), (Aman and Szpakowicz, 2007), (Brooks et al, 2013). However, only less amount work exists on emotion regression other than SemEval-2007 shared task (Strapparava andMihalcea, 2007).…”

Section: Introductionmentioning

confidence: 99%

deepCybErNet at EmoInt-2017: Deep Emotion Intensities in Tweets

Ravi

Premjith

Kumar

et al. 2017

Proceedings of the 8th Workshop on Computational Approaches To Subjectivity, Sentiment and Social Media Analysis

View full text Add to dashboard Cite

This working note presents the methodology used in deepCybErNet submission to the shared task on Emotion Intensities in Tweets (EmoInt) WASSA-2017. The goal of the task is to predict a real valued score in the range [0-1] for a particular tweet with an emotion type. To do this, we used Bag-of-Words and embedding based on recurrent network architecture. We have developed two systems and experiments are conducted on the Emotion Intensity shared Task 1 data base at WASSA-2017. A system which uses word embedding based on recurrent network architecture has achieved highest 5 fold crossvalidation accuracy. This has used embedding with recurrent network to extract optimal features at tweet level and logistic regression for prediction. These methods are highly language independent and experimental results shows that the proposed methods is apt for predicting a real valued score in than range [0-1] for a given tweet with its emotion type.

show abstract

“…Emotion detection in text is essentially a form of sentiment classification task based on finer-grained emotion categories. Automatic emotion detection has been applied in the domain of emails (Liu et al, 2003), customer reviews (Rubin, Stanton, & Liddy, 2004), children's stories (Alm et al, 2005), blog posts (Aman & Szpakowicz, 2007), newspaper headlines (Strapparava & Mihalcea, 2008), suicide notes (Pestian et al, 2012), and chat logs (Brooks et al, 2013). Early development of automatic emotion detectors focused only on the detection of Ekman's six basic emotions: happiness, surprise, sadness, fear, disgust, and anger (Alm et al, 2005;Aman & Szpakowicz, 2007;Liu et al, 2003;Strapparava & Mihalcea, 2008).…”

Section: Introductionmentioning

confidence: 99%

Expanding the Range of Automatic Emotion Detection in Microblogging Text

Liew

2014

Proceedings of the Student Research Workshop at the 14th Conference of the European Chapter of the Association for Computationa

View full text Add to dashboard Cite

Detecting emotions on microblogging sites such as Twitter is a subject of interest among researchers in behavioral studies investigating how people react to different events, topics, etc., as well as among users hoping to forge stronger and more meaningful connections with their audience through social media. However, existing automatic emotion detectors are limited to recognize only the basic emotions. I argue that the range of emotions that can be detected in microblogging text is richer than the basic emotions, and restricting automatic emotion detectors to identify only a small set of emotions limits their practicality in real world applications. Many complex emotions are ignored by current automatic emotion detectors because they are not programmed to seek out these "undefined" emotions. The first part of my investigation focuses on discovering the range of emotions people express on Twitter using manual content analysis, and the emotional cues associated with each emotion. I will then use the gold standard data developed from the first part of my investigation to inform the features to be extracted from text for machine learning, and identify the emotions that machine learning models are able to reliably detect from the range of emotions which humans can reliably detect in microblogging text.

show abstract

Statistical affect detection in collaborative chat

Cited by 49 publications

References 20 publications

Sentiment Mining from Text: A Technical Review

Sentiment Mining from Text: A Technical Review

deepCybErNet at EmoInt-2017: Deep Emotion Intensities in Tweets

Expanding the Range of Automatic Emotion Detection in Microblogging Text

Contact Info

Product

Resources

About