Twitter-based influenza detection after flu peak via tweets with indirect information: text mining study
Open accessPublished version of a preprint
Abstract
BACKGROUND: The recent rise in popularity and scale of social networking services (SNSs) has resulted in an increasing need for SNS-based information extraction systems. A popular application of SNS data is health surveillance for predicting an outbreak of epidemics by detecting diseases from text messages posted on SNS platforms. Such applications share the following logic: they incorporate SNS users as social sensors. These social sensor-based approaches also share a common problem: SNS-based surveillance are much more reliable if sufficient numbers of users are active, and small or inactive populations produce inconsistent results. OBJECTIVE: This study proposes a novel approach to estimate the trend of patient numbers using indirect information covering both urban areas and rural areas within the posts. METHODS: We presented a TRAP model by embedding both direct information and indirect information. A collection of tweets spanning 3 years (7 million influenza-related tweets in Japanese) was used to evaluate the model. Both direct information and indirect information that mention other places were used. As indirect information is less reliable (too noisy or too old) than direct information, the indirect information data were not used directly and were considered as inhibiting direct information. For example, when indirect information appeared often, it was considered as signifying that everyone already had a known disease, leading to a small amount of direct information. RESULTS: The estimation performance of our approach was evaluated using the correlation coefficient between the number of influenza cases as the gold standard values and the estimated values by the proposed models. The results revealed that the baseline model (BASELINE+NLP) shows .36 and that the proposed model (TRAP+NLP) improved the accuracy (.70, +.34 points). CONCLUSIONS: The proposed approach by which the indirect information inhibits direct information exhibited improved estimation performance not only in rural cities but also in urban cities, which demonstrated the effectiveness of the proposed method consisting of a TRAP model and natural language processing (NLP) classification.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
User-generated information and real-time information surveillance of various public health outcomes can identify cases of infectious diseases more quickly, which may permit investigation or action.
“Media and techniques known as user-generated information and real-time information surveillance of various public health outcomes, such as influenza, foodborne illnesses, or heat alerts, can identify cases of infectious diseases more quickly, which in the case of alerts, may permit investigation or action.”
From Social Media Role and Its Impact on Public Health: A Narrative Review (2023) · cites this paper as [17]
The Introduction (Background and Objective; page unavailable) describes Twitter users as sensors for detecting infectious-disease outbreaks and points to the speed of information transmission. The Discussion (Limitations and Future Direction; page unavailable) says earlier, accurate outbreak identification is a goal requiring further development. Our copy does not establish faster identification of individual cases, cover heat alerts, or say that alerts permit investigation or action. (LLM, conf=0.84)
Experimental — accuracy not yet measuredSocial media has an opportune disease surveillance area, improving its capability to detect disease outbreaks.
“The platform has an opportune disease surveillance area, improving its capability to detect disease outbreaks.”
From Social Media Role and Its Impact on Public Health: A Narrative Review (2023) · cites this paper as [17]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Detecting 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 · see citing works
Earthquake shakes Twitter users
Sakaki, T., Okazaki, M., & Matsuo, Y. (2010) · International World Wide Web Conference (WWW) · doi:10.1145/1772690.1772777 · Cited by 3,631 · see citing works
Eysenbach, G. (2009) · Journal of Medical Internet Research · doi:10.2196/jmir.1157 · Cited by 1,351 · see citing works
Signorini, A., Segre, A. M., & Polgreen, P. M. (2011) · PLoS ONE · doi:10.1371/journal.pone.0019467 · Cited by 1,234 · see citing works
Bäckström, L., Sun, E., & Marlow, C. (2010) · International World Wide Web Conference (WWW) · doi:10.1145/1772690.1772698 · Cited by 720 · see citing works
Towards detecting influenza epidemics by analyzing Twitter messages
Culotta, A. (2010) · doi:10.1145/1964858.1964874 · Cited by 622 · see citing works
Broniatowski, D. A., Paul, M., & Dredze, M. (2013) · PLoS ONE · doi:10.1371/journal.pone.0083672 · Cited by 474 · see citing works
Chunara, R., Andrews, J. R., & Brownstein, J. S. (2012) · American Journal of Tropical Medicine and Hygiene · doi:10.4269/ajtmh.2012.11-0597 · Cited by 437 · see citing works
Twitter earthquake detection: earthquake monitoring in a social world
Earle, P. S., Bowden, D. C., & Guy, M. R. (2012) · Annals of Geophysics · doi:10.4401/ag-5364 · Cited by 417 · see citing works
The Effects of Twitter Sentiment on Stock Price Returns
Ranco, G., Aleksovski, D., Caldarelli, G., Grčar, M., & Mozetič, I. (2015) · PLoS ONE · doi:10.1371/journal.pone.0138441 · Cited by 395 · cited 2× · see citing works
“Social media are used to detect various events, such as earthquakes [2-4], political elections [5-7], and stock prices in a market [8].”
BackgroundKirk, M. D., Pires, S. M., Black, R. E., Caipo, M., Crump, J. A., Devleesschauwer, B., Döpfer, D., Fazil, A., Fischer-Walker, C. L., Hald, T., et al. (2015) · PLOS Medicine · doi:10.1371/journal.pmed.1001940 · Cited by 346 · see citing works
Charles, L., Reynolds, T. L., Cameron, M. A., Conway, M., Lau, E. H. Y., Olsen, J. M., Pavlin, J. A., Shigematsu, M., Streichert, L. C., Suda, K. J., et al. (2015) · PLoS ONE · doi:10.1371/journal.pone.0139701 · Cited by 322 · see citing works
Twitter Improves Influenza Forecasting
Paul, M. J., Dredze, M. H., & Broniatowski, D. A. (2014) · PLoS Currents · doi:10.1371/currents.outbreaks.90b9ed0f59bae4ccaa683a39865d9117 · Cited by 244 · see citing works
Dengue surveillance based on a computational model of spatio-temporal locality of Twitter
Gomide, J., Veloso, A., Meira, W., Almeida, V. A. F., Benevenuto, F., Ferraz, F., & Teixeira, M. M. (2011) · ACM Web Science Conference (WebSci) · doi:10.1145/2527031.2527049 · Cited by 243 · see citing works
"I'm eating a sandwich in Glasgow"
Kinsella, S., Murdock, V., & O’Hare, N. (2011) · doi:10.1145/2065023.2065039 · Cited by 235 · see citing works
Geolocation Prediction in Social Media Data by Finding Location Indicative Words
Han, B., Cook, P., & Baldwin, T. (2012) · International Conference on Computational Linguistics · Cited by 166 · see citing works
Nagar, R., Yuan, Q., Freifeld, C. C., Santillana, M., Nojima, A., Chunara, R., & Brownstein, J. S. (2014) · Journal of Medical Internet Research · doi:10.2196/jmir.3416 · Cited by 156 · see citing works
Estimating Twitter User Location Using Social Interactions--A Content Based Approach
Chandra, S., Khan, L. R., & Muhaya, F. B. (2011) · doi:10.1109/passat/socialcom.2011.120 · Cited by 136 · see citing works
@Phillies Tweeting from Philly? Predicting Twitter User Locations with Spatial Word Usage
Chang, H.-W., Lee, D., Eltaher, M. A., et al. (2012) · IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) · doi:10.1109/asonam.2012.29 · Cited by 133 · see citing works
Combating Rumor Spread on Social Media: The Effectiveness of Refutation and Warning
Ozturk, P., Li, H., & Sakamoto, Y. (2015) · Hawaii International Conference on System Sciences (HICSS) · doi:10.1109/hicss.2015.288 · Cited by 126 · see citing works
Social Media as a Sensor of Air Quality and Public Response in China
Wang, S., Paul, M. J., & Dredze, M. H. (2015) · Journal of Medical Internet Research · doi:10.2196/jmir.3875 · Cited by 114 · see citing works
A large-scale quantitative analysis of latent factors and sentiment in online doctor reviews
Wallace, B., Paul, M. J., Sarkar, U., Trikalinos, T. A., & Dredze, M. H. (2014) · Journal of the American Medical Informatics Association · doi:10.1136/amiajnl-2014-002711 · Cited by 113 · see citing works
The spread of a rumor or infection in a moving population
Kesten, H., & Sidoravičius, V. (2005) · The Annals of Probability · doi:10.1214/009117905000000413 · Cited by 111 · see citing works
Social Monitoring for Public Health
Paul, M., & Dredze, M. (2017) · Synthesis Lectures on Information Concepts Retrieval and Services · doi:10.1007/978-3-031-02311-8 · Cited by 109 · see citing works
#Swineflu: Twitter Predicts Swine Flu Outbreak in 2009
Szomszor, M., Kostkova, P., & de Quincey, E. (2011) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-642-23635-8_3 · Cited by 89 · see citing works
Early Warning and Outbreak Detection Using Social Networking Websites: The Potential of Twitter
de Quincey, E., & Kostkova, P. (2010) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-642-11745-9_4 · Cited by 86 · see citing works
Using Twitter Sentiment to Forecast the 2013 Pakistani Election and the 2014 Indian Election
Kagan, V., Stevens, A., & Subrahmanian, V. S. (2015) · IEEE Intelligent Systems · doi:10.1109/mis.2015.16 · Cited by 81 · see citing works
Use of Hangeul Twitter to Track and Predict Human Influenza Infection
Kim, E.-K., Seok, J. H., Oh, J. S., Lee, H. W., & Kim, K. H. (2013) · PLoS ONE · doi:10.1371/journal.pone.0069305 · Cited by 78 · see citing works
TWITTER IMPROVES SEASONAL INFLUENZA PREDICTION
Achrekar, H., Gandhe, A., Lazarus, R. M., Yu, S.-H., & Liu, B. (2012) · International Conference on Health Informatics · doi:10.5220/0003780600610070 · Cited by 77 · see citing works
Influenza-Like Illness Surveillance on Twitter through Automated Learning of Naïve Language
Gesualdo, F., Stilo, G., Agricola, E., Gonfiantini, M. V., Pandolfi, E., Velardi, P., & Tozzi, A. E. (2013) · PLoS ONE · doi:10.1371/journal.pone.0082489 · Cited by 68 · see citing works
Modeling the impact of twitter on influenza epidemics
Pawelek, K. A., Oeldorf-Hirsch, A., & Rong, L. (2014) · Mathematical Biosciences & Engineering · doi:10.3934/mbe.2014.11.1337 · Cited by 59 · see citing works
A framework for detecting public health trends with Twitter
Parker, J. I., Wei, Y., Yates, A., Frieder, O., & Goharian, N. (2013) · IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) · doi:10.1145/2492517.2492544 · Cited by 58 · see citing works
On the Geo-Indicativeness of Non-Georeferenced Text
Adams, B., & Janowicz, K. (2021) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v6i1.14309 · Cited by 55 · see citing works
Earle, P. S. (2010) · Nature Geoscience · doi:10.1038/ngeo832 · Cited by 53 · see citing works
Singh, A. K., & Singh, Y. N. (2013) · Acta Physica Polonica B · doi:10.5506/aphyspolb.44.5 · Cited by 48 · see citing works
Mining Twitter big data to predict 2013 Pakistan election winner
Mahmood, T., Iqbal, T., Amin, F., et al. (2013) · doi:10.1109/inmic.2013.6731323 · Cited by 39 · see citing works
Doan, S., Lucila Ohno-machado, A., & Collier, N. (2012) · Cited by 39 · see citing works
Doan, S., Lucila Ohno-machado, A., & Collier, N. (2012) · IEEE International Conference on Healthcare Informatics, Imaging and Systems Biology · doi:10.1109/hisb.2012.21 · Cited by 32 · see citing works
Twitter, Public Opinion, and the 2011 Nigerian Presidential Election
Fink, C., Bos, N., Perrone, A., et al. (2013) · doi:10.1109/socialcom.2013.50 · Cited by 30 · see citing works
Real-time spatio-temporal analysis of West Nile virus using Twitter data
Sugumaran, R., & Voss, J. (2012) · doi:10.1145/2345316.2345361 · Cited by 21 · see citing works
Towards personalized learning to rank for epidemic intelligence based on social media streams
Diaz-Aviles, E., Stewart, A., Velasco, E., et al. (2012) · International World Wide Web Conference (WWW) · doi:10.1145/2187980.2188094 · Cited by 16 · see citing works
Portraying Collective Spatial Attention in Twitter
Antoine, É., Jatowt, A., Wakamiya, S., et al. (2015) · ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2783258.2783418 · Cited by 15 · see citing works
Self-citationWho caught a cold ? - Identifying the subject of a symptom
Kanouchi, S., Komachi, M., Okazaki, N., Aramaki, E., & Ishikawa, H. (2015) · doi:10.3115/v1/p15-1160 · Cited by 14 · see citing works
Self-citationWakamiya, S., Jatowt, A., Kawai, Y., et al. (2016) · doi:10.1145/2872518.2890551 · Cited by 10 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 6
- [15]Aramaki E Maskawa S Morita M Twitter catches the flu: detecting influenza epidemics using Twitter 2011 The Conference on Empirical Methods in Natural Language Processing (EMNLP) July 27-31, 2011 Edinburgh, United Kingdom Association for Computational Linguistics 1568 1576
- [16]Kanhabua N Romano S Stewart A Nejdl W Supporting temporal analytics for health-related events in microblogs 2012 The ACM International Conference on Information and Knowledge Management (CIKM) October 29-November 2, 2012 Maui, Hawaii, USA ACM 2686 2688
- [17]Lamb A Paul MJ Dredze M Separating fact from fear: tracking flu infections on Twitter 2013 The Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL) 2013 Atlanta, Georgia Association for Computational Linguistics 789 795
- [24]Morita M Maskawa S Aramaki E Comparison between social media and search activity as online human sensors for detection of influenza 2013 The International Symposium on Languages in Biology and Medicine (LBM) 2013 Tokyo, Japan 75 79
- [32]Iso H Wakamiya S Aramaki E Forecasting word model: Twitter-based influenza surveillance and prediction 2016 The International Conference on Computational Linguistics (COLING) December 11-17, 2016 Osaka, Japan The COLING 2016 Organizing Committee 76 86
- [39]Wakamiya S Morita M Kano Y Ohkuma T Aramaki E Overview of the NTCIR-13 MedWeb Task 2017 The NTCIR Conference on Evaluation of Information Access Technologies (NTCIR-13) December 5-8, 2017 Tokyo, Japan 40 49
Cited by
Sorted by citations
Google Trends in Infodemiology and Infoveillance: Methodology Framework
Mavragani, A., & Ochoa, G. (2019) · JMIR Public Health and Surveillance · doi:10.2196/13439 · Cited by 520 · see citing works
Social Media Role and Its Impact on Public Health: A Narrative Review
Kanchan, S., & Gaidhane, A. (2023) · Cureus · doi:10.7759/cureus.33737 · Cited by 221 · see citing works
“in 2018 using Twitter to detect Influenza outbreaks via geotagging tweets and trapped sensors supported the evidence [17].”
MethodConway, M., Hu, M., & Chapman, W. W. (2019) · Yearbook of Medical Informatics · doi:10.1055/s-0039-1677918 · Cited by 91 · see citing works
- Authors
- Wakamiya, S., Kawai, Y., & Aramaki, E.
- Affiliations
- Nara Institute of Science and Technology (JP)
- Kyoto Sangyo University (JP)
- Venue
- JMIR Public Health and Surveillance
- Publisher
- JMIR Publications Inc.
- Published
- 2018-09-25
- Volume
- 4
- Issue
- 3
- Pages
- e65
- ISSN
- 2369-2960 (ISSN-L)
- PMC
- PMC6231889
- OpenAlex
- W2884721711
- Cited by
- 75
- References
- 44
- Citations by year
- 2026: 4 · 2025: 6 · 2024: 8 · 2023: 11 · 2022: 12 · 2021: 14 · 2020: 11 · 2019: 7 · 2018: 2
- FWCI
- 6.64
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- JMIR Public Health and Surveillance (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- Japan Agency for Medical Research and Development
- Japan Society for the Promotion of Science (16H01722, 16K16057)
- Topics
- Health Sciences › Medicine › Epidemiology › Data-Driven Disease Surveillance
- Social Sciences › Health › Social Media in Health Education
- Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Toxicology › Pharmacovigilance and Adverse Drug Reactions
- Keywords
- influenza surveillance, Twitter, indirect information, trap model, epidemic forecasting, urban and rural areas, social sensors
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
