Tweet Emotion Dynamics: Emotion Word Usage in Tweets from US and Canada

• URL: http://arxiv.org/abs/2204.04862v1
• Date: Mon, 11 Apr 2022 04:39:39 GMT
• Title: Tweet Emotion Dynamics: Emotion Word Usage in Tweets from US and Canada
• Authors: Krishnapriya Vishnubhotla and Saif M. Mohammad
• Abstract summary: We introduce a massive dataset of more than 45 million geo-located tweets posted between 2015 and 2021 from US and Canada. We also introduce Tweet Emotion Dynamics (TED) -- metrics to capture patterns of emotions associated with tweets over time.
• Score: 34.41140246464486
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Over the last decade, Twitter has emerged as one of the most influential forums for social, political, and health discourse. In this paper, we introduce a massive dataset of more than 45 million geo-located tweets posted between 2015 and 2021 from US and Canada (TUSC), especially curated for natural language analysis. We also introduce Tweet Emotion Dynamics (TED) -- metrics to capture patterns of emotions associated with tweets over time. We use TED and TUSC to explore the use of emotion-associated words across US and Canada; across 2019 (pre-pandemic), 2020 (the year the pandemic hit), and 2021 (the second year of the pandemic); and across individual tweeters. We show that Canadian tweets tend to have higher valence, lower arousal, and higher dominance than the US tweets. Further, we show that the COVID-19 pandemic had a marked impact on the emotional signature of tweets posted in 2020, when compared to the adjoining years. Finally, we determine metrics of TED for 170,000 tweeters to benchmark characteristics of TED metrics at an aggregate level. TUSC and the metrics for TED will enable a wide variety of research on studying how we use language to express ourselves, persuade, communicate, and influence, with particularly promising applications in public health, affective science, social science, and psychology.

Related papers

• Socratis: Are large multimodal models emotionally aware? [63.912414283486555]
  Existing emotion prediction benchmarks do not consider the diversity of emotions that an image and text can elicit in humans due to various reasons. We propose Socratis, a societal reactions benchmark, where each image-caption (IC) pair is annotated with multiple emotions and the reasons for feeling them. We benchmark the capability of state-of-the-art multimodal large language models to generate the reasons for feeling an emotion given an IC pair.
  arXiv  Detail & Related papers  (2023-08-31T13:59:35Z)
• An Exploratory Study of Tweets about the SARS-CoV-2 Omicron Variant: Insights from Sentiment Analysis, Language Interpretation, Source Tracking, Type Classification, and Embedded URL Detection [0.0]
  This paper presents the findings of an exploratory study on the continuously generating Big Data on Twitter related to the COVID-19 pandemic. A total of 12028 tweets about the Omicron variant were studied, and the specific characteristics of tweets that were analyzed include - sentiment, language, source, type, and embedded URLs. To support similar research in this field, we have developed a Twitter dataset that comprises more than 500,000 tweets about the SARS-CoV-2 omicron variant since the first detected case of this variant on November 24, 2021.
  arXiv  Detail & Related papers  (2022-07-20T18:47:20Z)
• Negativity Spreads Faster: A Large-Scale Multilingual Twitter Analysis on the Role of Sentiment in Political Communication [7.136205674624813]
  This paper attempts to analyse tweets of politicians from three European countries. By utilising state-of-the-art pre-trained language models, we performed sentiment analysis on hundreds of thousands of tweets. Our analysis indicates that politicians' negatively charged tweets spread more widely, especially in more recent times.
  arXiv  Detail & Related papers  (2022-02-01T13:25:19Z)
• Extracting Feelings of People Regarding COVID-19 by Social Network Mining [0.0]
  dataset of COVID-related tweets in English language is collected. More than two million tweets from March 23 to June 23 of 2020 are analyzed.
  arXiv  Detail & Related papers  (2021-10-12T16:45:33Z)
• Changes in European Solidarity Before and During COVID-19: Evidence from a Large Crowd- and Expert-Annotated Twitter Dataset [77.27709662210363]
  We introduce the well-established social scientific concept of social solidarity and its contestation, anti-solidarity, as a new problem setting to supervised machine learning in NLP. We annotate 2.3k English and German tweets for (anti-)solidarity expressions, utilizing multiple human annotators and two annotation approaches (experts vs. crowds) Our results show that solidarity became increasingly salient and contested during the COVID-19 crisis.
  arXiv  Detail & Related papers  (2021-08-02T17:03:12Z)
• COVID-19 sentiment analysis via deep learning during the rise of novel cases [0.5156484100374059]
  We use deep learning based language models via long short-term memory (LSTM) recurrent neural networks for sentiment analysis on Twitter. We find that the majority of the tweets have been positive with high levels of optimism during the rise of the COVID-19 cases in India. We find that the optimistic and joking tweets mostly dominated the monthly tweets and there was a much lower number of negative sentiments expressed.
  arXiv  Detail & Related papers  (2021-04-05T04:31:19Z)
• Understanding the Hoarding Behaviors during the COVID-19 Pandemic using Large Scale Social Media Data [77.34726150561087]
  We analyze the hoarding and anti-hoarding patterns of over 42,000 unique Twitter users in the United States from March 1 to April 30, 2020. We find the percentage of females in both hoarding and anti-hoarding groups is higher than that of the general Twitter user population. The LIWC anxiety mean for the hoarding-related tweets is significantly higher than the baseline Twitter anxiety mean.
  arXiv  Detail & Related papers  (2020-10-15T16:02:25Z)
• Analyzing COVID-19 on Online Social Media: Trends, Sentiments and Emotions [44.92240076313168]
  We analyze the affective trajectories of the American people and the Chinese people based on Twitter and Weibo posts between January 20th, 2020 and May 11th 2020. By contrasting two very different countries, China and the Unites States, we reveal sharp differences in people's views on COVID-19 in different cultures. Our study provides a computational approach to unveiling public emotions and concerns on the pandemic in real-time, which would potentially help policy-makers better understand people's need and thus make optimal policy.
  arXiv  Detail & Related papers  (2020-05-29T09:24:38Z)
• Detecting Perceived Emotions in Hurricane Disasters [62.760131661847986]
  We introduce HurricaneEmo, an emotion dataset of 15,000 English tweets spanning three hurricanes: Harvey, Irma, and Maria. We present a comprehensive study of fine-grained emotions and propose classification tasks to discriminate between coarse-grained emotion groups.
  arXiv  Detail & Related papers  (2020-04-29T16:17:49Z)
• Word frequency and sentiment analysis of twitter messages during Coronavirus pandemic [0.0]
  The social networking site, Twitter, demonstrated similar effect with the number of posts related to coronavirus showing an unprecedented growth in a very short span of time. This paper presents a statistical analysis of the twitter messages related to this disease posted since January 2020. Results showed that the majority of the tweets had a positive polarity and only about 15% were negative.
  arXiv  Detail & Related papers  (2020-04-08T10:45:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.