Climate Change Sentiment on Twitter: An Unsolicited Public Opinion Poll

Cody, Emily M.; Reagan, Andrew J.; Mitchell, Lewis; Dodds, Peter Sheridan; Danforth, Christopher M.

doi:10.1371/journal.pone.0136092

Cited by 227 publications

(195 citation statements)

References 27 publications

Supporting

Mentioning

161

Contrasting

Unclassified

Order By: Relevance

“…The labMT, LIWC 2007, and ANEW unigram sentiment instruments were used to quantify the happiness of tweet language (3639). The use of labMT, which has shown strong prior performance in analyzing happiness on Twitter (40,41), is novel with respect to depression screening; ANEW and LIWC have been successfully applied in previous studies on depression and Twitter (7,8,14). LIWC was also used to compile frequency counts of various parts of speech (e.g., pronouns, verbs, adjectives) and semantic categories (e.g., food words, familial terms, profanity) as additional predictors (36).…”

Section: Feature Extractionmentioning

confidence: 99%

Forecasting the onset and course of mental illness with Twitter data

Reece

Reagan

Lix

et al. 2017

Sci Rep

Self Cite

296

226

View full text Add to dashboard Cite

We developed computational models to predict the emergence of depression and Post-Traumatic Stress Disorder in Twitter users. Twitter data and details of depression history were collected from 204 individuals (105 depressed, 99 healthy). We extracted predictive features measuring affect, linguistic style, and context from participant tweets (N = 279,951) and built models using these features with supervised learning algorithms. Resulting models successfully discriminated between depressed and healthy content, and compared favorably to general practitioners’ average success rates in diagnosing depression, albeit in a separate population. Results held even when the analysis was restricted to content posted before first depression diagnosis. State-space temporal analysis suggests that onset of depression may be detectable from Twitter data several months prior to diagnosis. Predictive results were replicated with a separate sample of individuals diagnosed with PTSD (Nusers = 174, Ntweets = 243,775). A state-space time series model revealed indicators of PTSD almost immediately post-trauma, often many months prior to clinical diagnosis. These methods suggest a data-driven, predictive approach for early screening and detection of mental illness.

show abstract

Section: Feature Extractionmentioning

confidence: 99%

Forecasting the onset and course of mental illness with Twitter data

Reece

Reagan

Lix

et al. 2017

Sci Rep

Self Cite

296

226

View full text Add to dashboard Cite

show abstract

“…For example, current studies infer network influence from self-reported survey data (Brody et al, 2008;Leombruni, 2015) rather than analyzing and constructing actual social networks. Yet, with the increasing spread and transmission of risk information on social media, new theories and methods are being developed, including "social contagion theories of risk" (Scherer & Cho, 2003), social tipping points (Kinzig et al, 2013; van der Linden, 2017), "sentiment" analyses on Twitter (Cody et al, 2015), and the role of network opinion leaders (Nisbet & Kotcher, 2009). In short, much exciting research remains to be done on the topic of normative influence and its impact on concern about global warming.…”

Section: Social and Cultural Influences The Social Construction Of Riskmentioning

confidence: 99%

Determinants and Measurement of Climate Change Risk Perception, Worry, and Concern

Linden¹

2017

Oxford Research Encyclopedia of Climate Science

120

117

View full text Add to dashboard Cite

and KeywordsIndividuals, both within and between different countries, vary substantially in the extent to which they view climate change as a risk. What could explain such variation in climate change risk perception around the world? Climate change is relatively unique as a risk in the sense that it is difficult for people to experience directly or even detect on a purely perceptual or sensory level. In fact, research across the social and behavioral sciences has shown that although people might correctly perceive some changes in long-term climate conditions, psychological factors are often much more influential in determining how the public perceives the risk of climate change. Indeed, decades of research has shown that cognitive, affective, social, and cultural factors all greatly influence the public's perception of risk, and that these factors, in turn, often interact with each other in complex ways. Yet, although a wide variety of cognitive, experiential, socio-cultural and demographic characteristics have all proven to be relevant, are there certain factors that systematically stand out in explaining and predicting climate change risk perception around the world? And even if so, what do we mean, exactly, by the term "risk perception" and to what extent does the way in which risk perception is measured influence the outcome? Last but certainly not least, how important is public concern about climate change in determining people's level of behavioral engagement and policysupport for the issue?

show abstract

“…Kirilenko and Stepchenkova [2] used a 1-million sample of tweets to research geographical variations in climate change discourse worldwide. Cody et al [3] analyzed 1.5 million tweets containing the words "climate" to explore temporal changes in sentiment (described in the paper as "a tool to measure happiness") expressed by the people in relation to climate change. Yang et al [4] researched the effect of climate and seasonality on depressed mood using automated content analysis of 600 million tweets.…”

Section: Introductionmentioning

confidence: 99%

Crowdsourcing Analysis of Twitter Data on Climate Change: Paid Workers vs. Volunteers

et al. 2017

View full text Add to dashboard Cite

Web based crowdsourcing has become an important method of environmental data processing. Two alternatives are widely used today by researchers in various fields: paid data processing mediated by for-profit businesses such as Amazon's Mechanical Turk, and volunteer data processing conducted by amateur citizen-scientists. While the first option delivers results much faster, it is not quite clear how it compares with volunteer processing in terms of quality. This study compares volunteer and paid processing of social media data originating from climate change discussions on Twitter. The same sample of Twitter messages discussing climate change was offered for processing to the volunteer workers through the Climate Tweet project, and to the paid workers through the Amazon MTurk platform. We found that paid crowdsourcing required the employment of a high redundancy data processing design to obtain quality that was comparable with volunteered processing. Among the methods applied to improve data processing accuracy, limiting the geographical locations of the paid workers appeared the most productive. Conversely, we did not find significant geographical differences in the accuracy of data processed by volunteer workers. We suggest that the main driver of the found pattern is the differences in familiarity of the paid workers with the research topic.

show abstract

Climate Change Sentiment on Twitter: An Unsolicited Public Opinion Poll

Cited by 227 publications

References 27 publications

Forecasting the onset and course of mental illness with Twitter data

Forecasting the onset and course of mental illness with Twitter data

Determinants and Measurement of Climate Change Risk Perception, Worry, and Concern

Crowdsourcing Analysis of Twitter Data on Climate Change: Paid Workers vs. Volunteers

Contact Info

Product

Resources

About