scholarly journals Automatic gender detection in Twitter profiles for health-related cohort studies

JAMIA Open ◽  
2021 ◽  
Vol 4 (2) ◽  
Author(s):  
Yuan-Chi Yang ◽  
Mohammed Ali Al-Garadi ◽  
Jennifer S Love ◽  
Jeanmarie Perrone ◽  
Abeed Sarker
Keyword(s):  
Social Media ◽  
Confidence Interval ◽  
Population Level ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Social Media Data ◽  
Health Related ◽  
Twitter Users ◽  
Gender Detection ◽  
Media Data

Abstract Objective Biomedical research involving social media data is gradually moving from population-level to targeted, cohort-level data analysis. Though crucial for biomedical studies, social media user’s demographic information (eg, gender) is often not explicitly known from profiles. Here, we present an automatic gender classification system for social media and we illustrate how gender information can be incorporated into a social media-based health-related study. Materials and Methods We used a large Twitter dataset composed of public, gender-labeled users (Dataset-1) for training and evaluating the gender detection pipeline. We experimented with machine learning algorithms including support vector machines (SVMs) and deep-learning models, and public packages including M3. We considered users’ information including profile and tweets for classification. We also developed a meta-classifier ensemble that strategically uses the predicted scores from the classifiers. We then applied the best-performing pipeline to Twitter users who have self-reported nonmedical use of prescription medications (Dataset-2) to assess the system’s utility. Results and Discussion We collected 67 181 and 176 683 users for Dataset-1 and Dataset-2, respectively. A meta-classifier involving SVM and M3 performed the best (Dataset-1 accuracy: 94.4% [95% confidence interval: 94.0–94.8%]; Dataset-2: 94.4% [95% confidence interval: 92.0–96.6%]). Including automatically classified information in the analyses of Dataset-2 revealed gender-specific trends—proportions of females closely resemble data from the National Survey of Drug Use and Health 2018 (tranquilizers: 0.50 vs 0.50; stimulants: 0.50 vs 0.45), and the overdose Emergency Room Visit due to Opioids by Nationwide Emergency Department Sample (pain relievers: 0.38 vs 0.37). Conclusion Our publicly available, automated gender detection pipeline may aid cohort-specific social media data analyses (https://bitbucket.org/sarkerlab/gender-detection-for-public).

scholarly journals Automatic Gender Detection in Twitter Profiles for Health-related Cohort Studies

2021 ◽  
Author(s):  
Yuan-Chi Yang ◽  
Mohammed Ali Al-Garadi ◽  
Jennifer S. Love ◽  
Jeanmarie Perrone ◽  
Abeed Sarker
Keyword(s):  
Social Media ◽  
Population Level ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Prescription Medications ◽  
Study Materials ◽  
Gender Information ◽  
Level Data ◽  
Health Related ◽  
Gender Detection

Objective Biomedical research involving social media (SM) data is gradually moving from population-level to targeted, cohort-level data analysis. Though crucial for biomedical studies, SM user's demographic information (e.g., gender) is often not explicitly known from profiles. Here we present an automatic gender classification system for SM and we illustrate how gender information can be incorporated into a SM-based health-related study. Materials and Methods We used two large Twitter datasets: (i) public, gender-labeled users (Dataset-1), and (ii) users who have self-reported nonmedical use of prescription medications (Dataset-2). Dataset-1 was used to train and evaluate the gender detection pipeline. We experimented with machine-learning algorithms including support vector machines (SVMs) and deep-learning models, and released packages including M3. We considered user's information including profile and tweets for classification. We also developed a meta-classifier ensemble that strategically uses the predicted scores from the classifiers. We applied the best-performing pipeline to Dataset-2 to assess the system's utility. Results and Discussion We collected 67,181 and 176,683 users for Dataset-1 and Dataset-2, respectively. A meta-classifier involving SVM and M3 performed the best (Dataset-1 accuracy: 94.4% [95%-CI: 94.0%-94.8%]; Dataset-2: Dataset-2: 94.4% [95%-CI: 92.0%-96.6%]. Including automatically-classified information in the analyses of Dataset-2 revealed gender-specific trends-proportions of females closely resemble data from the National Survey of Drug Use and Health 2018 (tranquilizers: 0.50 vs. 0.50; stimulants: 0.50 vs. 0.45), and the overdose Emergency Room Visit due to Opioids by CDC (pain relievers: 0.38 vs. 0.37). Conclusion Our publicly-available, automated gender detection pipeline may aid cohort-specific social media data analyses (https://bitbucket.org/sarkerlab/gender-detection-for-public).

scholarly journals Mining Social Media Data for Biomedical Signals and Health-Related Behavior

2020 ◽  
Vol 3 (1) ◽  
pp. 433-458 ◽  
Author(s):  
Rion Brattig Correia ◽  
Ian B. Wood ◽  
Johan Bollen ◽  
Luis M. Rocha
Keyword(s):  
Mental Health ◽  
Social Media ◽  
Population Level ◽  
Data Access ◽  
Health Conditions ◽  
Social Phenomena ◽  
Medical Treatments ◽  
Social Media Data ◽  
Health Related ◽  
Media Data

Social media data have been increasingly used to study biomedical and health-related phenomena. From cohort-level discussions of a condition to population-level analyses of sentiment, social media have provided scientists with unprecedented amounts of data to study human behavior associated with a variety of health conditions and medical treatments. Here we review recent work in mining social media for biomedical, epidemiological, and social phenomena information relevant to the multilevel complexity of human health. We pay particular attention to topics where social media data analysis has shown the most progress, including pharmacovigilance and sentiment analysis, especially for mental health. We also discuss a variety of innovative uses of social media data for health-related applications as well as important limitations of social media data access and use.

Daily and hourly mood pattern discovery of Turkish twitter users

2015 ◽  
Vol 5 (2) ◽  
pp. 90
Author(s):  
Mete Celik ◽  
Ahmet Sakir Dokuz
Keyword(s):  
Social Media ◽  
Big Data ◽  
Support Vector ◽  
Feature Selection Technique ◽  
Social Media Data ◽  
Web Technologies ◽  
Document Frequency ◽  
Social Media Text ◽  
Twitter Users ◽  
Media Data

<p>Massive amount of data-related applications and widespread usage of web technologies has started big data era. Social media data is one of the big data sources. Mining social media data provides useful insights for companies and organizations for developing their services, products or organizations. This study aims to analyze Turkish Twitter users based on daily and hourly social media sharings. By this way, daily and hourly mood patterns of Turkish social media users could be revealed in positive or negative manner. For this purpose, Support Vector Machines (SVM) classification algorithm and Term Frequency – Inverse Document Frequency (TF-IDF) feature selection technique was used. As far as our knowledge, this is the first attempt to analyze people’s all sharings on social media and generate results for temporal-based indicators like macro and micro levels.</p><p> </p><p>Keywords: big data, social media, text classification, svm, tf-idf term weighting, daily and hourly mood patterns.</p>

scholarly journals Automating Dynamic Consent Decisions for the Processing of Social Media Data in Health Research

2019 ◽  
Vol 15 (3) ◽  
pp. 187-201
Author(s):  
Chris Norval ◽  
Tristan Henderson
Keyword(s):  
Social Media ◽  
Health Research ◽  
User Study ◽  
Machine Learning Algorithms ◽  
Middle Ground ◽  
Social Media Data ◽  
Dynamic Consent ◽  
Significant Burden ◽  
Health Related ◽  
Media Data

Social media have become a rich source of data, particularly in health research. Yet, the use of such data raises significant ethical questions about the need for the informed consent of those being studied. Consent mechanisms, if even obtained, are typically broad and inflexible, or place a significant burden on the participant. Machine learning algorithms show much promise for facilitating a “middle-ground” approach: using trained models to predict and automate granular consent decisions. Such techniques, however, raise a myriad of follow-on ethical and technical considerations. In this article, we present an exploratory user study ( n = 67) in which we find that we can predict the appropriate flow of health-related social media data with reasonable accuracy, while minimizing undesired data leaks. We then attempt to deconstruct the findings of this study, identifying and discussing a number of real-world implications if such a technique were put into practice.

scholarly journals Insulin pricing and other major diabetes-related concerns in the USA: a study of 46 407 tweets between 2017 and 2019

2020 ◽  
Vol 8 (1) ◽  
pp. e001190
Author(s):  
Adrian Ahne ◽  
Francisco Orchard ◽  
Xavier Tannier ◽  
Camille Perchoux ◽  
Beverley Balkau ◽  
...  
Keyword(s):  
Social Media ◽  
Positive Emotions ◽  
Negative Impact ◽  
Diabetes Distress ◽  
Social Media Data ◽  
Health Related ◽  
The Usa ◽  
Personal Content ◽  
Design And Methods ◽  
Media Data

IntroductionLittle research has been done to systematically evaluate concerns of people living with diabetes through social media, which has been a powerful tool for social change and to better understand perceptions around health-related issues. This study aims to identify key diabetes-related concerns in the USA and primary emotions associated with those concerns using information shared on Twitter.Research design and methodsA total of 11.7 million diabetes-related tweets in English were collected between April 2017 and July 2019. Machine learning methods were used to filter tweets with personal content, to geolocate (to the USA) and to identify clusters of tweets with emotional elements. A sentiment analysis was then applied to each cluster.ResultsWe identified 46 407 tweets with emotional elements in the USA from which 30 clusters were identified; 5 clusters (18% of tweets) were related to insulin pricing with both positive emotions (joy, love) referring to advocacy for affordable insulin and sadness emotions related to the frustration of insulin prices, 5 clusters (12% of tweets) to solidarity and support with a majority of joy and love emotions expressed. The most negative topics (10% of tweets) were related to diabetes distress (24% sadness, 27% anger, 21% fear elements), to diabetic and insulin shock (45% anger, 46% fear) and comorbidities (40% sadness).ConclusionsUsing social media data, we have been able to describe key diabetes-related concerns and their associated emotions. More specifically, we were able to highlight the real-world concerns of insulin pricing and its negative impact on mood. Using such data can be a useful addition to current measures that inform public decision making around topics of concern and burden among people with diabetes.

scholarly journals Comprehensive scoping review of health research using social media data

BMJ Open ◽  
2018 ◽  
Vol 8 (12) ◽  
pp. e022931 ◽  
Author(s):  
Joanna Taylor ◽  
Claudia Pagliari
Keyword(s):  
Public Health ◽  
Social Media ◽  
Scoping Review ◽  
Ethical Issues ◽  
Social Media Data ◽  
Related Research ◽  
Health Related Research ◽  
Health Related ◽  
Google Search ◽  
Media Data

IntroductionThe rising popularity of social media, since their inception around 20 years ago, has been echoed in the growth of health-related research using data derived from them. This has created a demand for literature reviews to synthesise this emerging evidence base and inform future activities. Existing reviews tend to be narrow in scope, with limited consideration of the different types of data, analytical methods and ethical issues involved. There has also been a tendency for research to be siloed within different academic communities (eg, computer science, public health), hindering knowledge translation. To address these limitations, we will undertake a comprehensive scoping review, to systematically capture the broad corpus of published, health-related research based on social media data. Here, we present the review protocol and the pilot analyses used to inform it.MethodsA version of Arksey and O’Malley’s five-stage scoping review framework will be followed: (1) identifying the research question; (2) identifying the relevant literature; (3) selecting the studies; (4) charting the data and (5) collating, summarising and reporting the results. To inform the search strategy, we developed an inclusive list of keyword combinations related to social media, health and relevant methodologies. The frequency and variability of terms were charted over time and cross referenced with significant events, such as the advent of Twitter. Five leading health, informatics, business and cross-disciplinary databases will be searched: PubMed, Scopus, Association of Computer Machinery, Institute of Electrical and Electronics Engineers and Applied Social Sciences Index and Abstracts, alongside the Google search engine. There will be no restriction by date.Ethics and disseminationThe review focuses on published research in the public domain therefore no ethics approval is required. The completed review will be submitted for publication to a peer-reviewed, interdisciplinary open access journal, and conferences on public health and digital research.

scholarly journals Promoting Reproducible Research for Characterizing Nonmedical Use of Medications Through Data Annotation: Description of a Twitter Corpus and Guidelines

10.2196/15861 ◽  
2020 ◽  
Vol 22 (2) ◽  
pp. e15861 ◽  
Author(s):  
Karen O'Connor ◽  
Abeed Sarker ◽  
Jeanmarie Perrone ◽  
Graciela Gonzalez Hernandez
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Prescription Medication ◽  
Automatic Classification ◽  
Support Vector ◽  
Manual Annotation ◽  
Social Media Data ◽  
Nonmedical Use ◽  
Medication Abuse ◽  
Media Data

Background Social media data are being increasingly used for population-level health research because it provides near real-time access to large volumes of consumer-generated data. Recently, a number of studies have explored the possibility of using social media data, such as from Twitter, for monitoring prescription medication abuse. However, there is a paucity of annotated data or guidelines for data characterization that discuss how information related to abuse-prone medications is presented on Twitter. Objective This study discusses the creation of an annotated corpus suitable for training supervised classification algorithms for the automatic classification of medication abuse–related chatter. The annotation strategies used for improving interannotator agreement (IAA), a detailed annotation guideline, and machine learning experiments that illustrate the utility of the annotated corpus are also described. Methods We employed an iterative annotation strategy, with interannotator discussions held and updates made to the annotation guidelines at each iteration to improve IAA for the manual annotation task. Using the grounded theory approach, we first characterized tweets into fine-grained categories and then grouped them into 4 broad classes—abuse or misuse, personal consumption, mention, and unrelated. After the completion of manual annotations, we experimented with several machine learning algorithms to illustrate the utility of the corpus and generate baseline performance metrics for automatic classification on these data. Results Our final annotated set consisted of 16,443 tweets mentioning at least 20 abuse-prone medications including opioids, benzodiazepines, atypical antipsychotics, central nervous system stimulants, and gamma-aminobutyric acid analogs. Our final overall IAA was 0.86 (Cohen kappa), which represents high agreement. The manual annotation process revealed the variety of ways in which prescription medication misuse or abuse is discussed on Twitter, including expressions indicating coingestion, nonmedical use, nonstandard route of intake, and consumption above the prescribed doses. Among machine learning classifiers, support vector machines obtained the highest automatic classification accuracy of 73.00% (95% CI 71.4-74.5) over the test set (n=3271). Conclusions Our manual analysis and annotations of a large number of tweets have revealed types of information posted on Twitter about a set of abuse-prone prescription medications and their distributions. In the interests of reproducible and community-driven research, we have made our detailed annotation guidelines and the training data for the classification experiments publicly available, and the test data will be used in future shared tasks.

The Bigger Picture: Combining Econometrics with Analytics Improves Forecasts of Movie Success

2021 ◽  
Author(s):  
Steven F. Lehrer ◽  
Tian Xie
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Big Data ◽  
Predictive Analytics ◽  
Big Data Analytics ◽  
Forecast Accuracy ◽  
Support Vector ◽  
Significant Heterogeneity ◽  
Social Media Data ◽  
Media Data

There exists significant hype regarding how much machine learning and incorporating social media data can improve forecast accuracy in commercial applications. To assess if the hype is warranted, we use data from the film industry in simulation experiments that contrast econometric approaches with tools from the predictive analytics literature. Further, we propose new strategies that combine elements from each literature in a bid to capture richer patterns of heterogeneity in the underlying relationship governing revenue. Our results demonstrate the importance of social media data and value from hybrid strategies that combine econometrics and machine learning when conducting forecasts with new big data sources. Specifically, although both least squares support vector regression and recursive partitioning strategies greatly outperform dimension reduction strategies and traditional econometrics approaches in forecast accuracy, there are further significant gains from using hybrid approaches. Further, Monte Carlo experiments demonstrate that these benefits arise from the significant heterogeneity in how social media measures and other film characteristics influence box office outcomes. This paper was accepted by J. George Shanthikumar, big data analytics.

scholarly journals From FAIR data to fair data use: Methodological data fairness in health-related social media research

2021 ◽  
Vol 8 (1) ◽  
pp. 205395172110103
Author(s):  
Sabina Leonelli ◽  
Rebecca Lovell ◽  
Benedict W Wheeler ◽  
Lora Fleming ◽  
Hywel Williams
Keyword(s):  
Social Media ◽  
Well Being ◽  
Research Process ◽  
Future Research ◽  
Social Media Data ◽  
Data Practices ◽  
Health Related Research ◽  
Health Related ◽  
Use Of Social Media ◽  
Media Data

The paper problematises the reliability and ethics of using social media data, such as sourced from Twitter or Instagram, to carry out health-related research. As in many other domains, the opportunity to mine social media for information has been hailed as transformative for research on well-being and disease. Considerations around the fairness, responsibilities and accountabilities relating to using such data have often been set aside, on the understanding that as long as data were anonymised, no real ethical or scientific issue would arise. We first counter this perception by emphasising that the use of social media data in health research can yield problematic and unethical results. We then provide a conceptualisation of methodological data fairness that can complement data management principles such as FAIR by enhancing the actionability of social media data for future research. We highlight the forms that methodological data fairness can take at different stages of the research process and identify practical steps through which researchers can ensure that their practices and outcomes are scientifically sound as well as fair to society at large. We conclude that making research data fair as well as FAIR is inextricably linked to concerns around the adequacy of data practices. The failure to act on those concerns raises serious ethical, methodological and epistemic issues with the knowledge and evidence that are being produced.

Sign in / Sign up

Export Citation Format

Share Document