Extracting health-related causality from twitter messages using natural language processing

Doan, Son; Yang, Elly W.; Tilak, Sameer; Li, Peter W.; Zisook, Daniel S.; Torii, Manabu

doi:10.1186/s12911-019-0785-0

Cited by 54 publications

(45 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Recently, a growing body of literature has focused on examining the use of Twitter for public health research. 15,16,17 A systematic review identified six main uses of this social networking service for public health, and surveillance of public health or diseases is one of the topics described in the taxonomy. 18 Regarding oral health topics, to the best of our knowledge, only two studies have investigated twitter data for content related to dental treatment needs .19,20 Based on the current scenario, WHO postulated this line of research as an emerging scientific field and critical area of practice during a pandemic.…”

Section: Introductionmentioning

confidence: 99%

Self-reported dental treatment needs during the COVID-19 outbreak in Brazil: an infodemiological study

Oliveira

Zanatta

2020

Braz. oral res.

View full text Add to dashboard Cite

The aim of the present infodemiological study was to evaluate whether the COVID-19 outbreak has influenced the volume of content related to the dental treatment needs of Brazilian Twitter users to summarize the trends, and to identify the perceptions of the treatment needed. We collected tweets related to dental care needs of individuals exposed to the COVID-19 outbreak scenario between March 23 to May 4, 2020 and of those not exposed to the COVID-19 pandemic (unexposed group) on the same reported days of 2019 using the terms "dentista (dentist), dente (tooth), siso (third molar), and aparelho (orthodontic appliance)." Descriptive analysis was performed to provide summary statistics of the frequencies of tweets related to different dental treatment needs and also the differences in volume content between the years 2019 and 2020. Moreover, the data were analyzed by qualitative analysis using an inductive approach. A total of 1,763 tweets from 2020 and 1,339 tweets from 2019 were screened. Those tweets posted by non-Brazilian users, duplicates, and those unrelated to dental treatment needs were removed and, therefore 1,197 tweets from 2020 and 719 tweets from 2019 were selected. Content volume related to dental treatment needs greatly increased during the COVID-19 outbreak. Findings from the word cloud and content analysis suggest that dental pain, related or not to the third molar, and problems with orthodontic appliances were the topics most commonly related to dental treatment needs discussed during the COVID-19 outbreak, mainly conveying anxiety and distress. The volume of tweets related to dental treatment needs posted by Brazilian users increased during the COVID-19 outbreak and self-reported pain and urgencies were the most popular topics.

show abstract

Section: Introductionmentioning

confidence: 99%

Self-reported dental treatment needs during the COVID-19 outbreak in Brazil: an infodemiological study

Oliveira

Zanatta

2020

Braz. oral res.

View full text Add to dashboard Cite

show abstract

“…The list draws on phrases found in our study and in the references cited, particularly Hernan et al (10) and Thapa et al (6). We consider that a definition of causal language that is generally recognized by the research community is needed (22, 23).…”

Section: Discussionmentioning

confidence: 99%

Use of causal claims in observational studies: a research on research study

Parra

Bertizzolo

Schroter³

et al. 2020

Preprint

View full text Add to dashboard Cite

Objective: To evaluate the consistency of causal statements in the abstracts of observational studies published in The BMJ. Design: Research on research study. Data source: All cohort or longitudinal studies describing an exposure-outcome relationship published in The BMJ during 2018. We also had access to the submitted papers and reviewer reports. Main outcome measures: Proportion of published research papers with 'inconsistent' use of causal language in the abstract. Papers where language was consistently causal or non-causal were classified as 'consistently causal' or 'consistently not causal', respectively; those where causality may be inferred were classified as 'suggests causal'. For the 'inconsistent' papers, we then compared the published and submitted version. Results: Of 151 published research papers, 60 described eligible studies. Of these 60, we classified the causal language used as 'consistently causal' (13%), 'suggests causal' (35%), 'inconsistent' (20%) and 'consistently not causal'(32%). The majority of the 'Inconsistent' papers (92%) were already inconsistent on submission. The inconsistencies found in both submitted and published versions was mainly due to mismatches between objectives and conclusions. One section might be carefully phrased in terms of association while the other presented causal language. When identifying only an association, some authors jumped to recommending acting on the findings as if motivated by the evidence presented. Conclusion: Further guidance is necessary for authors on what constitutes a causal statement and how to justify or discuss assumptions involved. Based on screening these abstracts, we provide a list of expressions beyond the obvious 'cause' word which may inspire a useful more comprehensive compendium on causal language.

show abstract

“…In recent years, researchers have recognized that social media platforms can also provide important information related to public health [23][24][25][26][27][28]. Social media in general and Twitter in particular have been found to be useful and impactful resources in health-related studies [9].…”

Section: Plos Onementioning

confidence: 99%

“…Online social media is producing massive amounts of information on an unprecedented scale, with 19%-28% of all users participating in health discussions [8]. On Twitter, over 500 million users worldwide discuss their life experiences, social factors, lifestyle, and health conditions [9]. Users often share a combination of their health conditions, related symptoms, social factors and their impact on their health conditions rather than providing a suspected or final diagnosis.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Building a semantically annotated corpus for chronic disease complications using two document types

Alnazzawi¹

2021

PLoS ONE

View full text Add to dashboard Cite

Narrative information in electronic health records (EHRs) contains a wealth of information related to patient health conditions. In addition, people use Twitter to express their experiences regarding personal health issues, such as medical complaints, symptoms, treatments, lifestyle, and other factors. Both genres of text include different types of health-related information concerning disease complications and risk factors. Knowing detailed information about controlling disease risk factors has a great impact on modifying these risks and subsequently preventing disease complications. Text-mining tools provide efficient solutions to extract and integrate vital information related to disease complications hidden in the large volume of the narrative text. However, the development of text-mining tools depends on the availability of an annotated corpus. In response, we have developed the PrevComp corpus, which is annotated with information relevant to the identification of disease complications, underlying risk factors, and prevention measures, in the context of the interaction between hypertension and diabetes. The corpus is unique and novel in terms of the very specific topic in the biomedical domain and as an integration of information from both EHRs and tweets collected from Twitter. The annotation scheme was designed with guidance by a domain expert, and two further domain experts performed the annotation, resulting in a high-quality annotation, with agreement rate F-scores as high as 0.60 and 0.75 for EHRs and tweets, respectively.

show abstract

Extracting health-related causality from twitter messages using natural language processing

Cited by 54 publications

References 29 publications

Self-reported dental treatment needs during the COVID-19 outbreak in Brazil: an infodemiological study

Self-reported dental treatment needs during the COVID-19 outbreak in Brazil: an infodemiological study

Use of causal claims in observational studies: a research on research study

Building a semantically annotated corpus for chronic disease complications using two document types

Contact Info

Product

Resources

About