Temporal Patterns of Happiness and Information in a Global Social Network: Hedonometrics and Twitter
Open accessThe DOI matches its Crossref record; 65 of the 68 references it cites were found in a registry or an index.
Abstract
Individual happiness is a fundamental societal metric. Normally measured through self-report, happiness has often been indirectly characterized and overshadowed by more readily quantifiable economic indicators such as gross domestic product. Here, we examine expressions made on the online, global microblog and social networking service Twitter, uncovering and explaining temporal variations in happiness and information levels over timescales ranging from hours to years. Our data set comprises over 46 billion words contained in nearly 4.6 billion expressions posted over a 33 month span by over 63 million unique users. In measuring happiness, we construct a tunable, real-time, remote-sensing, and non-invasive, text-based hedonometer. In building our metric, made available with this paper, we conducted a survey to obtain happiness evaluations of over 10,000 individual words, representing a tenfold size improvement over similar existing word sets. Rather than being ad hoc, our word list is chosen solely by frequency of usage, and we show how a highly robust and tunable metric can be constructed and defended.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures

![Figure 2 Demonstration of robustness and tunability of our text-based hedonometer, and reasoning for choice of a specific metric. To measure the happiness of a given text, we first compute frequencies of all words; we then create an overall happiness score, Eq. (1) , as a weighted average of subsets of 10,222 individual word happiness assessments on a 1 to 9 scale, obtained through Mechanical Turk (see main text and Methods). In varying word sets by excluding stop words [58], we can systematically explore families of happiness metrics. In plot A, we show time series of average happiness for Twitter, binned by day, produced by different metrics. Each time series is generated by omitting words with as indicated in plot B, which shows the overall distribution of average happiness of individual words. For we use all words; as increases, we progressively remove words centered around the neutral evaluation of 5. Plot C provides a test for robustness through a pairwise comparison of all time series using Pearson's correlation coefficient. For , the time series show very strong mutual agreement. We choose (black curve in A and F, shown in B, white symbols in C, D, and E) for the present paper because of its excellent correlation in output with that of a wide range of , and for reasons concerning the following trade-offs. In A, we see that as the number of stop words increases, so does the variability of the time series, suggesting an improvement in instrument sensitivity. However, at the same time, we lose coverage of texts. Plot D first shows how the number of individual words for which we have evaluations decreases as increases. For , we have 3,686 individual words down from 10,222. Plot E next shows the percentage of the Twitter data set covered by each word list, accounting for word frequency; for , our metric uses 22.7% of all words. Lastly, in plot F (which uses plot A's legend), we show how coverage of words decreases with word rank. When , we incorporate all low rank words, with a decline beginning at rank 5,000. For , we see similar patterns with the maximum coverage declining; for , we see a maximum coverage of approximately 50%.](https://figures.cochat.ai/paper-figures/9ee1400e54384445affdaf17e661bc73/temporal-patterns-of-happiness-and-information-in-a-global-social-network-figure-2.jpg)















Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“following Dodds et al.'s (2011) hedonometrics study, all host names were changed into names that score 5 (i.e., neutral in sentiments) on a valence scale of 1 - 9: Neil for male and Marjorie for female.”
From When guests trust hosts for their words: Host description and trust in sharing economy (2018) · cites this paper as Dodds et al.'s (2011)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
A Mathematical Theory of Communication
Shannon, C. E. (1948) · Bell System Technical Journal · doi:10.1002/j.1538-7305.1948.tb01338.x · Cited by 88,486
SIMPSON, E. H. (1949) · Nature · doi:10.1038/163688a0 · Cited by 14,164
Osgood, C. E., Suci, G. J., & Tannenbaum, P. H. (1957) · Cited by 9,433
What is Twitter, a social network or a news media?
Kwak, H., Lee, C., Park, H., & Moon, S. (2010) · Proceedings of the 19th international conference on World wide web · doi:10.1145/1772690.1772751 · Cited by 6,652 · cited 1×
“Twitter’s user population is therefore a blend of individuals, groups of individuals, organizations, media outlets, and automated services such as bots [50], representing a kind of disaggregated, crowd-sourced media [51].”
BackgroundTwitter mood predicts the stock market
Bollen, J., Mao, H., & Zeng, X. (2011) · Journal of Computational Science · doi:10.1016/j.jocs.2010.12.007 · Cited by 5,206 · cited 1×
“gleaned from Twitter to predict stock market behavior [36].”
BackgroundJost, L. (2006) · Oikos · doi:10.1111/j.2006.0030-1299.14714.x · Cited by 4,669 · cited 1×
“We further focus our present work on our essential findings regarding temporal variations in happiness including: the overall time series; regular cycles at the scale of days and weeks; time series for subsets of tweets containing specific keywords; and detailed comparisons between texts at the level of individual wor…”
MethodInfluentialEnvironmental genome shotgun sequencing of the sargasso sea
Venter, J. C., Remington, K., Heidelberg, J. F., Halpern, A. L., Rusch, D., Eisen, J. A., Wu, D., Paulsen, I., Nelson, K. E., Nelson, W., et al. (2004) · Science · doi:10.1126/science.1093857 · Cited by 4,376 · cited 1×
“Accurate description through quantitative measurement is essential to the advancement of any scientific field, and the shift from being data scarce to data rich has revolutionized many areas [2–5] ranging from astronomy [6–8] to ecology and biology [9] to particle physics [10].”
BackgroundDetecting influenza epidemics using search engine query data
Ginsberg, J., Mohebbi, M. H., Patel, R. S., Brammer, L., Smolinski, M. S., & Brilliant, L. (2009) · Nature · doi:10.1038/nature07634 · Cited by 4,295
Quantitative Analysis of Culture Using Millions of Digitized Books
Michel, J.-B., Shen, Y. K., Aiden, A. P., Veres, A., Gray, M. K., The Google Books Team, Pickett, J. P., Hoiberg, D., Clancy, D., Norvig, P., et al. (2011) · Science · doi:10.1126/science.1199644 · Cited by 3,077 · cited 2×
“(English) [12,13], music lyrics (1960 to 2007) [23], and the New”
BackgroundA wandering mind is an unhappy mind
Killingsworth, M. A., & Gilbert, D. T. (2010) · Science · doi:10.1126/science.1192439 · Cited by 2,575 · cited 1×
“There is an important psychological distinction between an individual's current, experiential happiness”
Background
Research works printed but not linked: 4
- [19]Layard R 2005 Happiness London The Penguin Press
- [21]Lyubomirsky S 2007 The How of Happiness New York The Penguin Press
- [43]Mishne G 2005 Experiments with mood classification in blog posts. Style2005, 1st Workshop on Stylistic Analysis of Text for Information Access
- [60]Dodds PS Harris KD Kloumann IM Bliss CA Danforth CM 2011 Temporal patterns of happiness and information in a global social network: Hedonometrics and twitter. Draft version. Available at http://arxiv.org/abs/1101.5120v3. Accessed October 24, 2011 PMC3233600 22163266 · arXiv
Cited by
Items 501–600 of 841
Computational Sentiment Analysis: Promises and Pitfalls
Ophir, Y., & Walter, D. (2023) · Oxford University Press eBooks · doi:10.1093/oso/9780197520536.003.0007 · Cited by 7
Robustness of emotion extraction from 20th century English books
Acerbi, A., Lampos, V., & Bentley, R. A. (2013) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2013.6691663 · Cited by 7
“In the case of HED, we extract from the Google Books corpus the frequencies of 3, 686 words taken from a list of 10, 222 words provided in [17].”
BackgroundMethodResultInfluentialDoes the Strength of Sentiment Matter? A Regression Based Approach on Turkish Social Media
Ertugrul, A. M., Ertuğrul, I. Ö., & Acartürk, C. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-59569-6_16 · Cited by 6
Can Big Data Help Predict Financial Market Dynamics?: Evidence from the Korean Stock Market
Pyo, D.-J. (2017) · East Asian Economic Review · doi:10.2139/ssrn.2997832 · Cited by 6
Cross-city Analysis of Location-based Sentiment in User-generated Text
Stelzmüller, C., Tanzer, S., & Schedl, M. (2021) · International World Wide Web Conference (WWW) · doi:10.1145/3442442.3451889 · Cited by 6
“While most existing work quantifies sentiment in general [6] or in one city’s area, e.”
BackgroundKamila, S., Hasanuzzaman, M., Ekbal, A., & Bhattacharyya, P. (2019) · PLoS ONE · doi:10.1371/journal.pone.0211872 · Cited by 6
Measuring Organizational Consciousness Through E-Mail Based Social Network AnalysisPreprint
Gloor, P. A., & Colladon, A. F. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1502.04997 · Cited by 6
“Other researchers claim to have discovered traces of global consciousness for example in the Twittersphere (Dodds et al. 2011).”
BackgroundAdaptive Cities: A Cybernetic Perspective on Urban Systems.Preprint
Gershenson, C., Santi, P., & Ratti, C. (2016) · arXiv (Cornell University) · Cited by 9
Human Centered Tools for Analyzing Online Social Data
Brooks, M. (2015) · ResearchWorks at the University of Washington (University of Washington) · Cited by 12
A rare allergic reaction to sodium methohexital.
Reichert, E. F., & Bassett, P. A. (1972) · PubMed · Cited by 6
Vidgen, B. (2019) · Oxford University Research Archive (ORA) (University of Oxford) · doi:10.5287/ora-mz4nenmyp · Cited by 11
Towards Emotionally Intelligent Machines: Taking Social Contexts into Account
Lin, H. Y., Yu, H., Miao, C., & Qiu, L. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-39910-2_2 · Cited by 5
“These two categories of emotion words have been used to indicate temporal pattern of individual’s happiness on Facebook and Twitter [6] and emotional fluctuations over time on Twitter [10].”
BackgroundLei, A., Li, Y., Chiu, Y., Niu, Y., & Chang, T. (2024) · Environment Development and Sustainability · doi:10.1007/s10668-024-04724-0 · Cited by 7
“The research data mainly include questionnaires, statistical data, remote sensing analysis, and other technologies (Celemin et al., 2015; Dodds et al., 2011; Onnom et al., 2018), while research methods mainly include DEA model, multiple linear regression analysis, structural equation model, entropy…”
The Weekend Effect in Online Reviews
Bayerl, A., Schoenmueller, V., Goldenberg, J., & Stahl, F. (2026) · Journal of Marketing Research · doi:10.1177/00222437251391808 · Cited by 6
Srivastava, G. (2018) · International Conference on Telecommunications and Signal Processing (TSP) · doi:10.1109/tsp.2018.8441433 · Cited by 5
“Most dictionaries were optimized versions of dictionaries from [11], but others could easily be used in this analysis to fit other needs.”
MethodA city-wide examination of fine-grained human emotions through social media analysis
Siriaraya, P., Zhang, Y., Kawai, Y., Jeszenszky, P., & Jatowt, A. (2023) · PLoS ONE · doi:10.1371/journal.pone.0279749 · Cited by 5
“Higher levels of negative emotions during Tuesday and Wednesday could perhaps be explained by people trying to get through the middle of a working week [44].”
BackgroundSentiment-based User Profiles in Microblogging Platforms
Gutiérrez, F. J., & Poblete, B. (2015) · ACM Conference on Hypertext and Social Media (HT) · doi:10.1145/2700171.2791027 · Cited by 5
“In fact, several studies have been published on understanding the temporal patterns in people’s mood changes [8, 15], the relation between weather and emotions [16, 21], the influence of geographical location with mood [19, 22, 23, 26], and the influence of Twitter mood as a stock market predictor…”
BackgroundKlinger, R. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-59569-6_39 · Cited by 5
“, tales [3], blogs [4], and as a very popular domain, microblogs on Twitter [5].”
BackgroundInfluentialMeasuring Social Well Being in The Big Data Era: Asking or Listening?Preprint
Curti, M., Iacus, S. M., Porro, G., & Siletti, E. (2015) · Archivio Istituzionale della Ricerca (Universita Degli Studi Di Milano) · doi:10.48550/arxiv.1512.07271 · Cited by 5
“Dodds et al (2011) studied happiness with real-time, remote-sensing, and unobtrusive text-based hedonometer applied over 46 billion words contained in nearly 4,6 billion expressions posted over a 33 month by 63 million unique users.”
Hashtags in Plastic Surgery: A Sentiment Analysis of over 1 Million Tweets
Chopan, M., Sayadi, L. R., Clark, E. M., Arora, J. S., & Maguire, K. (2023) · Aesthetic Plastic Surgery · doi:10.1007/s00266-023-03340-z · Cited by 6
“Word-shift graphs are useful tools that delineate the underlying differences between various keywords (i.e. plastic vs. cosmetic surgery) [19].”
InfluentialA decomposition of book structure through ousiometric fluctuations in cumulative word-time
Fudolig, M. I., Alshaabi, T., Cramer, K., Danforth, C. M., & Dodds, P. S. (2023) · Humanities and Social Sciences Communications · doi:10.1057/s41599-023-01680-4 · Cited by 12
“Inspired by Vonnegut [Vonnegut 1999, 2010, 2005], Reagan et al. [2016] examined how smoothed, “distantly measured” [Moretti 2013] happiness scores [Dodds et al. 2011] vary across the length of a book.”
MethodSelf-citationSentiment and Presentiment in Twitter: Do Trends in Collective Mood “Feel the Future”?
Radin, D. I. (2023) · World Futures · doi:10.1080/02604027.2023.2216629 · Cited by 7
“Daily Twitter sentiment data were retrieved from www.hedonometer.org, a website hosted by the University of Vermont’s Complex Systems Center as part of a project in its Computational Story Lab (Alshaabi et al., 2021; Dodds et al., 2011, 2015).”
MethodEffect of Using Regression on Class Confidence Scores in Sentiment Analysis of Twitter Data
Ertuğrul, I. Ö., Ertugrul, A. M., & Çakici, R. (2014) · Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis (WASSA) · doi:10.3115/v1/w14-2622 · Cited by 5
“The second approach is using LabMT word list (Dodds et al., 2011) which includes scores for sentiment analysis.”
MethodDictionaries and Decision Trees for the 2019
Iserman, M., Nalabandian, T., & Ireland, M. E. (2019) · Workshop on Computational Linguistics and Clinical Psychology (CLPsych) · doi:10.18653/v1/w19-3025 · Cited by 8
Enthusiastic Fandom: Analyzing Tweets of Professional Baseball Fans
Mizuno, M., Sano, Y., & Sasahara, K. (2021) · Quarterly Journal of Marketing · doi:10.7222/marketing.2021.015 · Cited by 5
Nanshan, M., Zhang, N., Xun, X., & Cao, J. (2022) · Computational Statistics & Data Analysis · doi:10.1016/j.csda.2022.107483 · Cited by 5
“In computational sociology, public opinion sensing and trend analysis have emerged from the advent of the big data revolution (Dodds et al., 2011; Sloan and Morgan, 2015).”
Does solar activity affect human happiness?
Krištoufek, L. (2017) · Physica A Statistical Mechanics and its Applications · doi:10.1016/j.physa.2017.10.031 · Cited by 5
Blanco, K., Briceno, A., Steele, A., Tapia, J. F., McKay, J., Towers, S., & Yong, K. E. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1408.0694 · Cited by 5
“06 94 v1 [”
Dodds, P. S., Minot, J. R., Arnold, M., Alshaabi, T., Adams, J. L., Dewhurst, D. R., Reagan, A. J., & Danforth, C. M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.11305 · Cited by 5
“The instigation of our work here came from first noticing in June of 2018 that our Hedonometer’s happiness time series for English Twitter [29, 33, 34] had begun to apparently show increasing turbulence from the year 2016 on.”
BackgroundMethodInfluentialSelf-citationSocial Behavior and Mental Health: A Snapshot Survey under COVID-19 PandemicPreprint
Dhelim, S., Chen, L., Ning, H., Das, S. K., Nugent, C., Burns, D., Leavey, G., Pesch, D., & White, E. B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.08165 · Cited by 8
“Other works used other psychological dictionaries to extract linguistic features, such as Affective Norms for English Words (ANEW) [31].”
Haqiqatkhah, M. M., & Hamaker, E. L. (2024) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/duvqh · Cited by 5
Investigating Language Use by Polarised Groups on Twitter: A Case Study of the Bushfires
Nasim, M., Sharif, N., Bhandari, P., Weber, D., Wood, M., Falzon, L., & Kashima, Y. (2022) · Australasian Document Computing Symposium · doi:10.1145/3572960.3572979 · Cited by 6
“We measured the happiness scores on a per group basis and per users basis using a happiness dictionary [5], which contains about 10, 000 words in eight languages, each with a happiness score between 1 and 9.”
MethodUnited States of Mind under Uncertainty
Bae, S., Jo, S., & Shim, M. (2023) · Journal of Economic Behavior & Organization · doi:10.1016/j.jebo.2023.07.013 · Cited by 4
Baray, J., & Cliquet, G. (2024) · Managerial and Decision Economics · doi:10.1002/mde.4462 · Cited by 4
Analysis of Subjective City Happiness Index Based on Large Scale Microblog Data
Wu, K., Ma, J., Chen, Z., & Ren, P. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-25255-1_30 · Cited by 6
SINAI-EMMA: Vectores de Palabras para el Análisis de Opiniones en Twitter.
Martínez‐Cámara, E., Cumbreras, M. Á. G., Valdivia, M. T. M., & López, L. A. U. (2015) · Cited by 6
Understanding Emotional Expressions in Social Media Through Data Mining
Ranellucci, J., Poitras, E., Bouchet, F., Lajoie, S. P., & Hall, N. C. (2016) · Elsevier eBooks · doi:10.1016/b978-0-12-801857-6.00005-1 · Cited by 4
Measuring happiness in large population
Wenas, A., Sjahputri, S., Takwin, B., Primaldhi, A., & Muhamad, R. (2016) · IOP Conference Series Earth and Environmental Science · doi:10.1088/1755-1315/31/1/012023 · Cited by 5
“Therefore in accordance to finding from study by Dodds et al. and Pollyanna hypothesis [3], tendency toward positivity bias is also present in corpus used in this study.”
BackgroundMethodInfluentialDiscussion: Plastic Surgery and Social Media: Examining Perceptions
Blankensteijn, L. L., & Lin, S. J. (2019) · Plastic & Reconstructive Surgery · doi:10.1097/prs.0000000000005446 · Cited by 4
The emotional arcs of political narratives
Drăgan, N.-S. (2020) · Bulletin of the Transilvania University of Brasov Series IV Philology and Cultural Studies · doi:10.31926/but.pcs.2020.62.13.3.6 · Cited by 4
Blockbuster or bust? Silver screen effect and stock returns
Hong, S., & Wei, X. (2025) · European Finance Review · doi:10.1093/rof/rfaf004 · Cited by 4
Effect of using regression in sentiment analysis
Ertuğrul, I. Ö., & Ertugrul, A. M. (2014) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2014.6830606 · Cited by 4
“[10] çalışmasının ekinde sunulan ve sentiment analizi için sözcüklerin çeşitli skorlarını içeren LabMT kullanılmasıdır.”
RWebData: A High-Level Interface to the Programmable Web
Matter, U. (2018) · Journal of Open Research Software · doi:10.5334/jors.201 · Cited by 4
Newman, M. E. J. (2018) · Oxford University Press eBooks · doi:10.1093/oso/9780198805090.003.0017 · Cited by 5
Garcia, D., Drejing, K., Amato, C., Kosiński, M., & Sikström, S. (2018) · Frontiers in Psychology · doi:10.3389/fpsyg.2018.01623 · Cited by 4
Repeatable measurement of Twitter user impact NASA and the great American Eclipse of 2017
Pickering, D., Shumay, M., & Srivastava, G. (2018) · Filomat · doi:10.2298/fil1805607p · Cited by 4
“Most dictionaries were used from [3], but others could easily be used in this analysis to fit other needs.”
MethodSentiment analysis for the tweets that contain the word “earthquake”
Pirnau, M. (2018) · European Conference on Artificial Intelligence · doi:10.1109/ecai.2018.8678958 · Cited by 5
“The circumplex model of affect elaborated by Russell [12] uses two concepts: the discrete emotions and the affection features and is used nowadays in a wide variety of domains, including in software systems for the sentiment analysis of the Twitter posts [20-22].”
MethodLussier, J. T., & Chawla, N. V. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-24477-3_18 · Cited by 6
“Other papers have taken various approaches to tweet sentiment analysis, including the study performed by Dodds et al that reports a steady global happiness level with weekly and daily patterns [4].”
BackgroundQuantifying Chinese Happiness via Large-Scale Microblogging Data
Kuang, C., Liu, Z., Sun, M., Yu, F., & Ma, P. (2014) · Web Information System and Application Conference · doi:10.1109/wisa.2014.48 · Cited by 4
“Peter Sheridan Dodds et al.[4] built their metric word list for happiness after analysing temporal patterns of happiness and information content for the very large data set generated by Twitter.”
BackgroundOn the quest of discovering cultural trails in social media
García-Gavilanes, R. (2013) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/2433396.2433490 · Cited by 4
“In social media, we can combine studies made on happiness in blogs and microblogs such as in the work of Dodds et al. [5, 6] with this dimension.”
MethodHyperlocal Happiness from Tweets
Quercia, D. (2015) · Cambridge University Press eBooks · doi:10.1017/cbo9781316182635.006 · Cited by 6
TED Talk Recommender Using Speech Transcripts
Oh, J., Lee, I., Seonwoo, Y., Sung, S., Kwon, I., & Lee, J.-G. (2018) · IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) · doi:10.1109/asonam.2018.8508644 · Cited by 4
“• Step1: We derived positive and negative scores from the transcripts using language assessment by Mechanical Turk (labMT) [7].”
MethodSykora, M. D., Elayan, S., Angelini, L., Röcke, C., Kamali, M. E., Mugellini, E., & Guye, S. (2021) · Research for development · doi:10.1007/978-3-030-72663-8_11 · Cited by 6
Early Warning Signals of Tipping-Points in Blog Posts
Slater, D. M. (2012) · Cited by 4
Sadasivuni, S. T., & Zhang, Y. (2021) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw53433.2021.00115 · Cited by 4
A Mixed-Methods Approach to Ethical Data Extraction in Social Media Studies
Hall, M. (2018) · SAGE Publications Ltd eBooks · doi:10.4135/9781526445681 · Cited by 4
Quillivic, R., Auxéméry, Y., Gayraud, F., Dayan, J., & Mesmoudi, S. (2025) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocaf075 · Cited by 3
Rossouw, S., & Greyling, T. (2026) · Applied Research in Quality of Life · doi:10.1007/s11482-025-10535-w · Cited by 6
“…importance of distinguishing between life evalua - tion and emotional experiences, while sentiment analysis from platforms like Twitter, Facebook (Dodds et al., 2011; Iacus et al., 2015; Schwartz et al., 2016; Greyling & Rossouw, 2019) and search engine data from Google Trends (Foa et al., 2022;…”
Microblogging without Borders:Differences and Similarities
García, R. A. D. F., Poblete, B., Mendoza, M., & Jaimes, A. (2011) · Cited by 3
Utilizing Artificial Intelligence to Make Systems Engineering More Human
Barry, P., & Doskey, S. C. (2020) · Wiley eBooks · doi:10.1002/9781119698821.ch3 · Cited by 4
Sentiment Analysis and Emotion Detection of COVID-19 Geo-Tagged Twitter Data
Wang, S., Dhakal, S., & Upadhyay, B. P. (2024) · IEEE International Conference on Big Data Analytics (ICBDA) · doi:10.1109/icbda61153.2024.10607368 · Cited by 3
“…Twitter-RoBERTa-base model [4], FlairNLP text classifier [5] as well as rule-based sentiment analysis tool Valence Aware Dictionary and sEntiment Reasoner (VADER) [6] and dictionary-based hedonometer, and Happiness Score by LabMT [7][8][9], which is a significant predictor of mental illness [10].”
BackgroundMethodInfluentialVizer, L. M., Pierce, J., Ji, Y., Bucher, M. A., Liu, M., Ungar, L., Giorgi, S., Xing, Z., House, S. L., Beaudoin, F. L., et al. (2025) · NPP—Digital Psychiatry and Neuroscience · doi:10.1038/s44277-025-00028-x · Cited by 3
“Validated language models of emotion calculated estimated levels of psychological traits such as personality [12], loneliness [13], politeness [14], depression [15], stress [16], emotion categories [17], and sentiment [18 – 20].”
Mapping Human Landscapes in Muscat, Oman, with Social Media Data
Tomarchio, L. (2019) · Repository for Publications and Research Data (ETH Zurich) · doi:10.3929/ethz-b-000339868 · Cited by 4
Towards Using Social Media to Identify Individuals at Risk for Preventable Chronic Illness
Bell, D., Fried, D., Huangfu, L., Surdeanu, M., & Kobourov, S. (2016) · Language Resources and Evaluation Conference (LREC) · doi:10.63317/5cjdfy7ddmr6 · Cited by 3
CIEA: A Corpus for Chinese Implicit Emotion Analysis
Li, D., Wang, J., & Zhang, X. (2019) · International Conference on Asian Language Processing · doi:10.1109/ialp48816.2019.9037667 · Cited by 3
“There are many works on exploiting corpora to promote the development of NLP. Previous sentiment analysis involved multiple text types, including product [3], movie reviews [4], fairy tales [5], news stories, social com mentary and commentary articles [6], blogs [7] [8] and microblogs [9].”
BackgroundCharacterizing Topics in Social Media Using Dynamics of Conversation
Flamino, J., Gong, B., Buchanan, F., & Szymanski, B. K. (2021) · Entropy · doi:10.3390/e23121642 · Cited by 4
“Moreover, while extracting user reactions has been seen as an essential tool for social media analysis for a while [2–5], most implementations tend to be limited to analyzing verbal responses using natural language processing (NLP) and the quantification of baseline interest.”
MethodHan, N., Huang, H., Wang, J., Shi, B., & Li, R. (2022) · Complexity · doi:10.1155/2022/4733305 · Cited by 3
Newman, M. E. J. (2018) · Oxford University Press eBooks · doi:10.1093/oso/9780198805090.003.0011 · Cited by 3
Predicting happiness contagion on online social networks
Lin, C.-Y., & Li, Y.-L. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-11989-y · Cited by 3
“[7] employed the Word Rating List from Amazon ’ s Mechanical Turk to evaluate the happiness score for each individual word.”
BackgroundMethodInfluentialTomarchio, L., He, P., Herthogs, P., & Tunçer, B. (2023) · International Journal on Smart and Sustainable Cities · doi:10.1142/s2972426023400020 · Cited by 6
Lê, V. Q. (2024) · Energy Systems · doi:10.1007/s12667-023-00652-6 · Cited by 3
Language Statistics at Different Spatial, Temporal, and Grammatical Scales
Sánchez-Puig, F., Lozano-Aranda, R., Pérez-Méndez, D., Colman, E. R., Morales, A. J., Torres, P. J. R., Pineda, C., & Gershenson, C. (2024) · Entropy · doi:10.3390/e26090734 · Cited by 3
“Our aim is to determine the significance of each scale in language statistics, evaluating how changes in these scales influence rank dynamics.”
The Pulse of Mood Online: Unveiling Emotional Reactions in a Dynamic Social Media Landscape
Guo, S., He, Z., Rao, A., Morstatter, F., Brantingham, P. J., & Lerman, K. (2024) · ACM Transactions on the Web · doi:10.1145/3708513 · Cited by 6
“These studies revealed that the sentiment of aggregated tweets exhibited distinct hourly, diurnal, and weekly mood patterns [17, 20].”
Quantifying collective mood by emoticon networks
Sasahara, K. (2014) · ACM Web Science Conference (WebSci) · doi:10.1145/2615569.2615658 · Cited by 3
“Quantifying Collective Mood by Emoticon Networks Kazutoshi Sasahara Graduate School of Information Science, Nagoya University Furo-cho Chikusa-ku Nagoya 464-8601, Japan sasahara@nagoya-u.jp ABSTRACT Emoticon networks are proposed to quantify the nontrivial nature of collective mood in social media.”
Backgroundmib at SemEval-2016 Task 4a: Exploiting lexicon based features for Sentiment Analysis in Twitter
Cozza, V., & Petrocchi, M. (2016) · International Workshop on Semantic Evaluation (SemEval) · doi:10.18653/v1/s16-1019 · Cited by 3
Social Media Trends and Prediction of Subjective Well-Being: A Literature Review
Singh, S., & Kaur, P. D. (2017) · Advances in intelligent systems and computing · doi:10.1007/978-981-10-3770-2_70 · Cited by 3
“Hedonometer has been made available publically on the internet 11 and is very useful to the researchers for future references.”
BackgroundSubjective well-being prediction from social networks: A review
Singh, S., & Kaur, P. D. (2016) · International Conference on Parallel, Distributed and Grid Computing (PDGC) · doi:10.1109/pdgc.2016.7913121 · Cited by 3
“The text-based Hedonometer [23] based on ANEW, which measures individuals happiness of Twitter users.”
MethodHappiness Index in Social Network
Singh, K., Shakya, H. K., & Biswas, B. (2017) · Communications in computer and information science · doi:10.1007/978-981-10-5780-9_24 · Cited by 3
Knowledge Flows and Influence in Online Social Networks: Proposing a Research Agenda
Weber, C. M., & Mayande, N. V. (2017) · Portland International Conference on Management of Engineering and Technology (PICMET) · doi:10.23919/picmet.2017.8125344 · Cited by 3
Consumers and Households: Materialism, Nonmaterialism, and Subjective Well-Being
Antonides, G., & van Klaveren, C. (2018) · Cambridge University Press eBooks · doi:10.1017/9781316676349.012 · Cited by 3
Mayande, N. V., & Weber, C. M. (2018) · Portland International Conference on Management of Engineering and Technology (PICMET) · doi:10.23919/picmet.2018.8481830 · Cited by 3
“The data have been analyzed in daily intervals, in order to capture tweet volatility patterns caused by daily routine (Dodds et al., [17]) .”
BackgroundResultLee, K., & Kim, I.-G. (2020) · Sustainability · doi:10.3390/su12208528 · Cited by 3
AWESSOME: An Unsupervised Sentiment Intensity Scoring Framework Using Neural Word Embeddings
Htait, A., & Azzopardi, L. A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-72240-1_56 · Cited by 3
Social Synchrony in Online Social Networks and its Application in Event Detection from Twitter Data
Sivaraman, N. K., Muthiah, S. B., Agarwal, P., & Todwal, L. (2020) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wiiat50758.2020.00067 · Cited by 3
“There are a few works on concepts similar to social synchrony in online social networks [16] [3], in the literature.”
BackgroundNewman, M. E. J. (2018) · Oxford University Press eBooks · doi:10.1093/oso/9780198805090.003.0018 · Cited by 4
Temporal models of streaming Social Media data
Preoțiuc-Pietro, D. (2014) · White Rose eTheses Online (University of Leeds, The University of Sheffield, University of York) · Cited by 4
Constructing a taxonomy of fine-grained human movement and activity motifs through social mediaPreprint
Frank, M. R., Williams, J. R., Mitchell, L., Bagrow, J. P., Dodds, P. S., & Danforth, C. M. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1410.1393 · Cited by 3
Self-citationReagan, A. J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.06163 · Cited by 4
Sentiment Quantification of User-Generated Content
Sebastiani, F. (2017) · Springer eBooks · doi:10.1007/978-1-4614-7163-9_110170-1 · Cited by 3
The Impact of Public Mood on the Cross-Section of Stock ReturnsPreprint
Marsh, I. W., & Liu, J. (2018) · SSRN Electronic Journal · doi:10.2139/ssrn.3170954 · Cited by 5
“Hedonometer.org reports that there are about 20 million tweets per day and approximately 14,000 per minute as at August 31 2011 Dodds et al. (2011).11 A day is considered happier than usual if happy words are used more frequently than usual, or if sad words are used less frequently than usual.”
BackgroundRussian Holidays Predict Troll Activity 2015-2017
Almond, D. V., Du, X., & Vogel, A. (2020) · National Bureau of Economic Research · doi:10.3386/w28035 · Cited by 3
Extended $s$-wave pairing symmetry on the triangular lattice heavy fermion systemPreprint
Zhang, L., Wang, Y.-F., Zhong, Y., & Luo, H. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1507.00160 · Cited by 3
Twitter Subjective Well-Being Indicator During COVID-19 Pandemic: A Cross-Country Comparative StudyPreprint
Carpi, T., Hino, A., Iacus, S. M., & Porro, G. (2021) · RePEc: Research Papers in Economics · doi:10.48550/arxiv.2101.07695 · Cited by 3
“Dodds et al. (2011) built an happiness indicator, called hedonometer, based on a so-called ‘closed vocabulary’ approach: they measured the frequency of use of a set of ten thousand words for which they have obtained happiness evaluations on a nine-point scale, using Mechanical Turk3.”
MethodSentiment Quantification of User-Generated Content
Sebastiani, F. (2018) · Springer eBooks · doi:10.1007/978-1-4939-7131-2_110170 · Cited by 4
Exploring sentiment in social media and official statistics: a general framework
Sulis, E., Lai, M., Vinai, M., & Sanguinetti, M. (2015) · Cited by 9
Samskara: Minimal structural features for detecting subjectivity and polarity in Italian tweets
Russo, I., & Monachini, M. (2016) · Accademia University Press eBooks · doi:10.4000/books.aaccademia.2023 · Cited by 2
Collective emotion regulation.
Goldenberg, A., & Cao, Y. (2026) · American Psychologist · doi:10.1037/amp0001729 · Cited by 3
Yong, K. S., & Yan, J. L. S. (2023) · Journal of Intelligent Information Systems · doi:10.1007/s10844-023-00791-3 · Cited by 2
“For example, emotion keyword hashtags such as #happy, #joy or #cheerful can be used to retrieve self-labeled tweets containing expressions of happiness from Twitter.”
BackgroundInfluentialAparecido, T. D. D., Carrillo, A., Camargo, C. Q., & Stella, M. (2025) · AI · doi:10.3390/ai6100249 · Cited by 5
Metadata
- Authors
- Dodds, P. S., Harris, K. D., Kloumann, I. M., Bliss, C. A., & Danforth, C. M.
- Affiliations
- University of Vermont (US)
- Corresponding author
- Dodds, Peter Sheridan
- Danforth, Christopher M.
- Venue
- PLoS ONE
- Publisher
- Public Library of Science (PLoS)
- Published
- 2011-12-07
- Volume
- 6
- Issue
- 12
- Pages
- e26752
- ISSN
- 1932-6203 (ISSN-L)
- PMC
- PMC3233600
- OpenAlex
- W2099366530
- Semantic Scholar
- 09f692cf26f283a22484443cc07aa7cc1f8e70f0
- Cited by
- 809
- References
- 68
- Citations by year
- 2026: 17 · 2025: 32 · 2024: 43 · 2023: 49 · 2022: 58 · 2021: 72 · 2020: 66 · 2019: 53 · 2018: 90 · 2017: 77 · 2016: 64 · 2015: 67 · 2014: 62 · 2013: 35 · 2012: 18
- FWCI
- 52.64
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- PLoS ONE (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- ScholarWorks -A service of University of Vermont Libraries (University of Vermont) (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Figshare (submittedVersion, cc-by)
- arXiv (Cornell University)
- Funders
- National Science Foundation (CAREER, 0846668)
- National Aeronautics and Space Administration
- Office of Experimental Program to Stimulate Competitive Research
- Topics
- Social Sciences › Psychology › Social Psychology › Psychological Well-being and Life Satisfaction
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Social Sciences › Psychology › Social Psychology › Mental Health via Writing
- Keywords
- happiness, Twitter, social networks, temporal patterns, subjective well-being, information level, word frequency
- MeSH terms
- Emotions, Happiness, Humans, Language, Social Behavior, Social Support, Software, Work, Models, Statistical, Internet, Blogging, Social Networking
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.