CrystalFeel at SemEval-2018 Task 1: Understanding and Detecting
            Emotion Intensity using Affective Lexicons

Gupta, Raj Kumar; Yang, Yinping

doi:10.18653/v1/s18-1038

Cited by 33 publications

(20 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies analyzed the four emotions in different periods of the pandemic using the CrystalFeel algorithm ( Garcia & Berton, 2021 b; Lwin et al, 2020 b; Shah et al, 2021 ), which has been proven in recent works to be accurate. In this study, the emotional strength scores of the CrystalFeel algorithm (R. K. Gupta & Yang, 2018 ) were used to label the dominant emotions of fear, anger, sadness, and joy at different phases of the pandemic according to the timeline of WHO tweets and U.S news during the ongoing Covid-19 pandemic. In the CrystalFeel algorithm, topics are labeled based on emotion score (i.e., emotional valence refers to feelings’ polarity) in three different categories including: (i) No-specific emotion, (ii) If valence-score is higher than 0.520, then the emotion category is “joy”; (iii) If valence-score is lower than 0.480, then the emotion category is: (1) “anger” if and only if the anger intensity-score is higher than both the fear and sadness intensity-scores, (2) “fear” if and only if the fear intensity-score is higher than both the and sadness intensity-scores, and (3) “sadness” if and only if sadness intensity-score is higher than both the anger and fear intensity-scores ( Garcia & Berton, 2021 b).…”

Section: Methodsmentioning

confidence: 99%

“…This study, address this gap by collecting tweets generated from January 2020 to May 2021 and by analyzing the public opinions and emotions by applying advanced machine learning technique, including the latent Dirichlet allocation (LDA) topic ( Blei et al, 2003 ) and CrystalFeel algorithm ( Gupta & Yang, 2018 ). More importantly, the extraction of different categories of content features and the building of a predictive model that assesses the popularity of tweets by using the number of retweets (based on the content of posted tweets) is another gap in the literature that we addressed in this study.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting the popularity of tweets by analyzing public opinion and emotions in different stages of Covid-19 pandemic

Mahdikhani

2022

International Journal of Information Management Data Insights

View full text Add to dashboard Cite

In this study, public opinion and emotions regarding different stages of the Covid-19 pandemic from the outbreak of the disease to the distribution of vaccines were analyzed to predict the popularity of tweets. More than 1.25 million English tweets were collected, posted from January 20, 2020, to May 29, 2021. Five sets of content features, including topic analysis, topics plus TF-IDF vectorizer, bag of words (BOW) by TF-IDF vectorizer, document embedding, and document embedding plus TF-IDF vectorizer, were extracted and applied to supervised machine learning algorithms to generate a predictive model for the retweetability of posted tweets. The analysis showed that tweets with higher emotional intensity are more popular than tweets containing information on Covid-19 pandemic. This study can help to detect the public emotions during the pandemic and after vaccination and predict the retweetability of posted tweets in different stages of Covid-19 pandemic.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Predicting the popularity of tweets by analyzing public opinion and emotions in different stages of Covid-19 pandemic

Mahdikhani

2022

International Journal of Information Management Data Insights

View full text Add to dashboard Cite

show abstract

“…If sentic patterns are not matched, the input sentence will be processed through hybrid Sentic-LSTM [56], a sentiment-augmented LSTM on a bag of concepts, to obtain a sentiment polarity value. In addition, the emotions of PORs were analyzed further using the algorithm CrystalFeel (www.crystalfeel.socialanalyticsplus.net accessed on 15 August 2020, [57]), a high-accuracy sentiment analytic tool.…”

Section: Sentiment Analysismentioning

confidence: 99%

Detecting Topic and Sentiment Trends in Physician Rating Websites: Analysis of Online Reviews Using 3-Wave Datasets

Shah

Jeong

2021

IJERPH

View full text Add to dashboard Cite

(1) Background: Physician rating websites (PRWs) are a rich resource of information where individuals learn other people response to various health problems. The current study aims to investigate and analyze the people top concerns and sentiment dynamics expressed in physician online reviews (PORs). (2) Methods: Text data were collected from four U.S.-based PRWs during the three time periods of 2018, 2019 and 2020. Based on the dynamic topic modeling, hot topics related to different aspects of healthcare were identified. Following the hybrid approach of aspect-based sentiment analysis, the social network of prevailing topics was also analyzed whether people expressed positive, neutral or negative sentiments in PORs. (3) Results: The study identified 30 dominant topics across three different stages which lead toward four key findings. First, topics discussed in Stage III were quite different from the earlier two stages due to the COVID-19 outbreak. Second, based on the keyword co-occurrence analysis, the most prevalent keywords in all three stages were related to the treatment, questions asked by patients, communication problem, patients’ feelings toward the hospital environment, disease symptoms, time spend with patients and different issues related to the COVID-19 (i.e., pneumonia, death, spread and cases). Third, topics related to the provider service quality, hospital servicescape and treatment cost were the most dominant topics in Stages I and II, while the quality of online information regarding COVID-19 and government countermeasures were the most dominant topics in Stage III. Fourth, when zooming into the topic-based sentiments analysis, hot topics in Stage I were mostly positive (joy be the dominant emotion), then negative (disgust be the dominant emotion) in Stage II. Furthermore, sentiments in the initial period of Stage III (COVID-19) were negative (anger be the dominant emotion), then transformed into positive (trust be the dominant emotion) later. The findings also revealed that the proposed method outperformed the conventional machine learning models in analyzing topic and sentiment dynamics expressed in PRWs. (4) Conclusions: Methodologically, this research demonstrates the ability and importance of computational techniques for analyzing large corpora of text and complementing conventional social science approaches.

show abstract

“…Recently, sentiment analysis techniques are very advanced, and many software are openly available, such as Stanford's CoreNLP, CrystalFeel, VADER, SenticNet, SentiStrength, and SentiCircles. The sentiment analysis in the current study was based on CrystalFeel algorithm, a sentiment analytics tool whose accuracy had been well-established (Gupta & Yang, 2018). This model categorized each emotion into four discrete emotions in Plutchik's framework of emotions (Plutchik, 2001), including joy, surprise, and trust (positive), and anger, fear, sadness, and disgust (negative).…”

Section: Sentiment Analysismentioning

confidence: 99%

Tracking patients healthcare experiences during the COVID-19 outbreak: Topic modeling and sentiment analysis of doctor reviews

Shah

Yan

Tariq³

et al. 2021

JER is an international, peer-reviewed journal that publishes f

View full text Add to dashboard Cite

Emerging voices of patients in the form of opinions and expectations about the quality of care can improve healthcare service quality. A large volume of patients’ opinions as online doctor reviews (ODRs) are available online to access, analyze, and improve patients’ perceptions. This paper aims to explore COVID-19-related conversations, complaints, and sentiments using ODRs posted by users of the physician rating website. We analyzed 96,234 ODRs of 5,621 physicians from a prominent health rating website in the United Kingdom (Iwantgreatcare.org) in threetime slices (i.e., from February 01 to October 31, 2020). We employed machine learning approach, dynamic topic modeling, to identify prominent bigrams, salient topics and labels, sentiments embedded in reviews and topics, and patient-perceived root cause and strengths, weaknesses, opportunities, and threats (SWOT) analyses to examine SWOT for healthcare organizations. This method finds a total of 30 latent topics with 10 topics across each time slice. The current study identified new discussion topics about COVID-19 occurring from time slice 1 to time slice 3, such as news about the COVID-19 pandemic, violence against the lockdown, quarantine process and quarantine centers at different locations, and vaccine development/treatment to stop virus spread. Sentiment analysis reveals that fear for novel pathogen prevails across all topics. Based on the SWOT analysis, our findings provide a clue for doctors, hospitals, and government officials to enhance patients’ satisfaction and minimize dissatisfaction by satisfying their needs and improve the quality of care during the COVID-19 crisis.

show abstract

CrystalFeel at SemEval-2018 Task 1: Understanding and Detecting Emotion Intensity using Affective Lexicons

Cited by 33 publications

References 24 publications

Predicting the popularity of tweets by analyzing public opinion and emotions in different stages of Covid-19 pandemic

Predicting the popularity of tweets by analyzing public opinion and emotions in different stages of Covid-19 pandemic

Detecting Topic and Sentiment Trends in Physician Rating Websites: Analysis of Online Reviews Using 3-Wave Datasets

Tracking patients healthcare experiences during the COVID-19 outbreak: Topic modeling and sentiment analysis of doctor reviews

Contact Info

Product

Resources

About