--- title: "Using Hedges to Enhance a Disease Outbreak Report Text" description: "The authors observe that outbreak news tends to be tentative, because early reports… 90.9% accuracy. 5 references, cited by 4 papers here." authors: ["Mike Conway", "Son Doan", "Nigel Collier"] year: 2009 venue: "Proceedings of the BioNLP 2009 Workshop" source: "https://aclanthology.org/W09-1318/" licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)" licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/conway-2009-hedges-enhance-disease-outbreak-report/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/conway-2009-hedges-enhance-disease-outbreak-report/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2009](https://md.research.elamur.ai/free/en/papers/2009/page/2/) / Using Hedges to Enhance a Disease Outbreak Report Text Mining System # Using Hedges to Enhance a Disease Outbreak Report Text Mining System **Authors:** [Mike Conway](https://md.research.elamur.ai/free/en/authors/mike-conway/), Son Doan and [Nigel Collier](https://md.research.elamur.ai/free/en/authors/nigel-collier/) · **Year:** 2009 · **Venue:** [Proceedings of the BioNLP 2009 Workshop](https://md.research.elamur.ai/free/en/venues/bionlp/) ([BioNLP 2009](https://md.research.elamur.ai/free/en/venues/bionlp/2009/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY-NC-SA 3.0 (ACL Anthology, before 2016)](https://creativecommons.org/licenses/by-nc-sa/3.0/) **Links:** [Publisher's page](https://aclanthology.org/W09-1318/) · [PDF](https://aclanthology.org/W09-1318.pdf) · [OpenAlex](https://openalex.org/W1984187075) **Citations:** 13 citations (OpenAlex, 2026-10-14) · [4](https://md.research.elamur.ai/free/en/papers/conway-2009-hedges-enhance-disease-outbreak-report/cited-by/) in our library, of the 149,439 papers whose bibliographies we read ## Summary Systems that watch online news for early signs of infectious disease outbreaks must separate real outbreak reports from articles that only mention a disease, such as stories about vaccination campaigns or research. The authors observe that outbreak news tends to be tentative, because early reports describe situations that are not yet confirmed. They apply this observation to the BioCaster system in two ways. First, they add a single binary hedge feature to BioCaster's n-gram topic classifier. The feature fires when a word from the Mercer et al. (2004) hedge lexicon appears within five words of a disease named entity. They test it on the BioCaster corpus of 1000 annotated news articles. For an SVM, the feature raises accuracy modestly, though a larger χ² 9000 n-gram feature set still performs best. Second, they build a "speculative" score. A document's hedge density is placed against tertile cut-points calculated from 10,000 Reuters documents, which yields a LOW, MEDIUM or HIGH tag. Relevant outbreak reports fall into HIGH much more often than rejected articles do. This suggests that uncertainty markers carry genuine signal for surveillance. ## Key points - The BioCaster corpus has 1000 news articles from sources such as BBC, the New York Times and ProMED-Mail. Each article is labelled relevant (350) or reject (650) and annotated with named entities. Borderline cases were included on purpose, and the corpus is not publicly released. - The hedge lexicon is adapted from Mercer et al. (2004). It is described as 72 verbs (including inflected forms) plus 32 non-verbs, and elsewhere in the paper as 105 lexemes. A χ² test showed that hedge frequency differs between the two classes at P \< 0.01. The most discriminating hedges include *reported*, *suspected*, *probable* and *suspect*. - Classification results: - With an SVM, unigrams give 90.9% accuracy (F 0.87), and unigrams plus the hedge feature give 91.7% (F 0.89). - With Naive Bayes, adding the hedge feature does not help (88.4 → 88.0). - The χ² 9000 n-gram set with Naive Bayes is the best result at 94.8% (F 0.93). - The speculative metric uses length-normalised hedge percentages from 10,000 Reuters documents to set tertile boundaries. LOW is ≤0.2544%, MEDIUM is up to about 1.0574%, and HIGH is anything above that. - Distribution of the speculative tag by class: | Tag | Relevant articles | Rejected articles | |---|---|---| | HIGH | 64.2% | 48.3% | | MEDIUM | 29.5% | 36.7% | | LOW | 6.3% | 15.0% | ## Interesting ideas - **Anchor hedges to an entity.** A hedge only counts when it occurs near the entity that matters (a disease mention), so general vagueness elsewhere in the text is ignored and precision improves. - **Calibrate a scale on a reference corpus.** Graded labels come from tertiles of a feature's distribution in a general reference corpus, not from thresholds picked by hand. Each label then has a clear, reproducible meaning. - **Treat speculative news as a genre signal.** Early, unconfirmed reports about events are marked by hedging, so the density of hedges says something about what kind of text a document is. - **Test one interpretable feature in isolation.** Adding a single interpretable feature to a baseline, and checking it across two learners, shows whether that linguistic cue adds real value. - **Rank words with χ² within a fixed lexicon.** Running χ² selection inside a known hedge lexicon shows which entries actually discriminate in a domain; here, *reported* and *suspected* dominate in news. ## For Mova How these ideas could serve Mova, our small open language model — its files, stages and tests: - **I1** (frames): Uncertainty markers could be attached to the specific frame whose argument they are near, instead of the whole sentence. This would give a local, explainable epistemic flag on "who did what to whom." - **I2** (world): Certainty or speculativeness levels attached to world states could be calibrated against a neutral news corpus, so that "highly speculative" is a documented percentile rather than an arbitrary number. - **I3** (answer): A reader answering questions could use hedge density to soften its answers ("reportedly", "suspected") when the source text is tentative, rather than stating claims as established facts. - **I4** (learn): Each new hand-built cue could be evaluated as one ablation against a baseline under more than one model, as a control against attributing gains to the cue by mistake. - **I5** (tokens): Lemma-level markers in the en crate could carry a domain-weighted strength, with the weights derived from similar χ² rankings on target corpora. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* ## Institutions - [National Institute of Informatics](https://md.research.elamur.ai/free/en/labs/national-institute-of-informatics/) — Research institute, Tokyo, Japan · 38 works · 3,247 citations - [Vanderbilt University Medical Center](https://md.research.elamur.ai/free/en/hospitals/vanderbilt-university-medical-center/) — Hospital, Nashville, United States · 3 works · 18 citations 📚 Shelves (8): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [🧬 Biochemistry, Genetics and Molecular Biology](https://md.research.elamur.ai/free/en/shelves/biochemistry-genetics-and-molecular-biology/) · 263 works · [🧬 Molecular Biology](https://md.research.elamur.ai/free/en/shelves/biochemistry-genetics-and-molecular-biology/molecular-biology/) · 260 works · [🩺 Medicine](https://md.research.elamur.ai/free/en/shelves/medicine/) · 275 works · [🩺 Epidemiology](https://md.research.elamur.ai/free/en/shelves/medicine/epidemiology/) · 7 works ## Cite Cite as: Mike Conway, Son Doan and Nigel Collier. 2009. Using Hedges to Enhance a Disease Outbreak Report Text Mining System. Proceedings of the BioNLP 2009 Workshop. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{conway2009using, title = {{Using Hedges to Enhance a Disease Outbreak Report Text Mining System}}, author = {Mike Conway, Son Doan and Nigel Collier}, booktitle = {Proceedings of the BioNLP 2009 Workshop}, year = {2009}, doi = {10.3115/1572364.1572384}, url = {https://doi.org/10.3115/1572364.1572384} } ``` - [← previous Presupposed Content and Entailments in Natural Language Inference](https://md.research.elamur.ai/free/en/papers/clausen-2009-presupposed-content-entailments-natural-language/) - [next → Comparison of Classification and Ranking Approaches to Pronominal Anaphora Resolution in Czech](https://md.research.elamur.ai/free/en/papers/ngy-2009-comparison-classification-ranking-approaches-pronominal/) - [↑ back to papers of 2009](https://md.research.elamur.ai/free/en/papers/2009/page/2/) ## References 5 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. N. Collier, S. Doan, A. Kawazoe, R. Matsuda-Goodwin, M. Conway, Y. Tateno, Q-H. Ngo, D. Dien, A. Kawtrakul, K. Takeuchi, M. Shigematsu, and K. Tanigu-ichi. 2008. BioCaster: Detecting Public Health Rumors with a Web-based Text Mining System. Bioinformatics, 24(24):2940–2941. [find](https://scholar.google.com/scholar?q=N%2E+Collier%2C+S%2E+Doan%2C+A%2E+Kawazoe%2C+R%2E+Matsuda%2DGoodwin%2C+M%2E+Conway%2C+Y%2E+Tateno%2C+Q%2DH%2E+Ngo%2C+D%2E+Dien%2C+A%2E+Kawtrakul%2C+K%2E+Takeuchi%2C+M%2E+Shigematsu%2C+and+K%2E+Tanigu%2Dichi%2E+2008%2E+BioCaster%3A+Detecting+Public+Health+Rum) 2. M. Conway, S. Doan, A. Kawazoe, and N. Collier. 2008. Classifying Disease Outbreak Reports Using N-grams and Semantic Features. Proceedings of the Third International Symposium on Semantic Mining in Biomedicine (SMBM 2008), Turku, Finland, pages 29– 36. [find](https://scholar.google.com/scholar?q=M%2E+Conway%2C+S%2E+Doan%2C+A%2E+Kawazoe%2C+and+N%2E+Collier%2E+2008%2E+Classifying+Disease+Outbreak+Reports+Using+N%2Dgrams+and+Semantic+Features%2E+Proceedings+of+the+Third+International+Symposium+on+Semantic+Mining+in+B) 3. K. Hyland. 1998. [Hedging in Scientific Research Articles](https://md.research.elamur.ai/free/en/papers/hyland-1998-hedging-scientific-research-articles/). John Benjamins, Amsterdam. 4. H. Kilicoglu and S. Bergler. 2008. [Recognizing Speculative Language in Biomedical Research Articles: a Linguistically Motivated Perspective](https://md.research.elamur.ai/free/en/papers/kilicoglu-2008-recognizing-speculative-language-biomedical-research/). BMC Bioinformatics, 9(Suppl 11):S10. 5. R. Mercer, C. DiMarco, and F. Kroon. 2004. The Frequency of Hedging Cues in Citation Contexts in Scientific Writing. In Proceedings of the Canadian Conference on AI, pages 75–88. 4 Reuters Corpus, Volume 1, English language, 1996-08-20 to 1997-08-19 (Release date 2000-11-03, Format version 1, correction level 0). [find](https://scholar.google.com/scholar?q=R%2E+Mercer%2C+C%2E+DiMarco%2C+and+F%2E+Kroon%2E+2004%2E+The+Frequency+of+Hedging+Cues+in+Citation+Contexts+in+Scientific+Writing%2E+In+Proceedings+of+the+Canadian+Conference+on+AI%2C+pages+75%E2%80%9388%2E+4+Reuters+Corpus%2C+Vol) *Updated 2 November 2026*