Buzz e-sante
248.4K views | +49 today
Buzz e-sante
Le média du digital santé
Curated by Rémy TESTON
Your new post is loading...
Your new post is loading...
Rescooped by Rémy TESTON from Social Media and Healthcare
January 27, 2015 7:44 AM
Scoop.it!

Discovering Health Topics in Social Media Using Topic Models

Discovering Health Topics in Social Media Using Topic Models | Buzz e-sante | Scoop.it
Abstract

By aggregating self-reported health statuses across millions of users, we seek to characterize the variety of health information discussed in Twitter. We describe a topic modeling framework for discovering health topics in Twitter, a social media website. This is an exploratory approach with the goal of understanding what health topics are commonly discussed in social media. This paper describes in detail a statistical topic model created for this purpose, the Ailment Topic Aspect Model (ATAM), as well as our system for filtering general Twitter data based on health keywords and supervised classification. We show how ATAM and other topic models can automatically infer health topics in 144 million Twitter messages from 2011 to 2013. ATAM discovered 13 coherent clusters of Twitter messages, some of which correlate with seasonal influenza (r = 0.689) and allergies (r = 0.810) temporal surveillance data, as well as exercise (r = .534) and obesity (r = −.631) related geographic survey data in the United States. These results demonstrate that it is possible to automatically discover topics that attain statistically significant correlations with ground truth data, despite using minimal human supervision and no historical data to train the model, in contrast to prior work. Additionally, these results demonstrate that a single general-purpose model can identify many different health topics in social media.

Figures    

Citation:Paul MJ, Dredze M (2014) Discovering Health Topics in Social Media Using Topic Models. PLoS ONE 9(8): e103408. doi:10.1371/journal.pone.0103408

Editor: Renaud Lambiotte, University of Namur, Belgium

Received: January 7, 2014; Accepted: July 2, 2014; Published: August 1, 2014

Copyright: © 2014 Paul, Dredze. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Funding:Mr. Paul was supported in part by a National Science Foundation Graduate Research Fellowship under Grant No. DGE-0707427 and a PhD fellowship from Microsoft Research. Publication of this article was funded in part by the Open Access Promotion Fund of the Johns Hopkins University Libraries. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

Competing interests: Dr. Dredze reports receipt of compensation for travel for talks at various academic, corporate, and governmental entities and consulting for Directing Medicine, Progeny Systems, and Sickweather. Mr. Paul serves on the advisory board for Sickweather. This does not alter the authors' adherence to PLOS ONE policies on sharing data and materials.

Introduction

Several studies have utilized social media for tracking trends and analyzing real world events, including news events, [1] natural disasters, [2] user sentiment, [3] and political opinions. [4]–[5]Twitter is an especially compelling source of social media data, with over half a billion user-generated status messages (“tweets”) posted every day, often publicly and easily accessible with streaming tools. [6] By aggregating the words used by millions of people to express what they are doing and thinking, automated systems can approximately infer what is happening around the world. Researchers have begun to tap into social media feeds to monitor and study health issues, [7] with applications in disease surveillance and other epidemiological analysis.

By far the most commonly analyzed disease in social media is influenza. Many researchers have tracked influenza in social media data, most commonly Twitter, using a variety of techniques such as linear regression, [8]–[10] supervised classification, [11]–[12] and social network analysis. [13] Researchers have also used social media to study cholera, [14] dental pain, [15] and cardiac arrest, [16] as well as population behavior including physical activities,[17] mood and mental health, [18]–[19] and alcohol, [9], [20] tobacco, [21] and drug use. [22]Twitter has a desirable property of being a real time data source, in contrast to surveys and surveillance networks that can take weeks or even years to deliver information. Additionally, users of Twitter may candidly share information that they do not provide to their doctor, and thus it is potentially a source of new information, such as off-label use of medications. [23], [24].

Studies like these rely on the detection of specific illnesses such as influenza or health topics such as exercise. In this work, we instead describe how to perform discovery of ailments and health topics. We do this using topic models, which automatically infer interesting patterns in large text corpora. We believe an exploratory, discovery-driven approach can serve us a useful starting point for medical data mining of social media, by automatically identifying and characterizing the health topics that are prominently discussed on social media. Our goal is not to improve modeling of any one specific illness, but to demonstrate a model for illness discovery. While we may validate the discovered illnesses against specialized approaches for tracking each specific illness, the strength of our model is that it allows discovery of new illness in new data without a priori knowledge. Furthermore, our list of discovered illnesses contains several that have previously been unexplored in Twitter, suggesting new areas for directed research, described in the Discussion section.

In this paper, we describe a statistical topic modeling framework for identifying general public health information from millions of health-related tweets. In addition to a basic topic model, we also describe our Ailment Topic Aspect Model (ATAM), previously used to analyze tweets from 2009–10. [24] This framework is used to explore the diversity of health topics that are discussed on Twitter, and we find that many health topics correlate with existing survey data. Our specific contributions are: (1) we describe a current end-to-end framework for data collection and analysis, which includes multiple data streams, keyword filters, and supervised classifiers for identifying relevant data; (2) we analyze a set of 144 million health-related tweets that we have been downloading continuously since August 2011; (3) we provide many previously unpublished details about the creation of our classifier for identifying health tweets and details of ATAM, our specialized health topic model, including procedures for large-scale inference; (4) we evaluate this framework and topic model quality by comparing temporal and geographic trends in the data with external data sources. We experiment with both a basic topic model and ATAM, as well as individual keyword filters for comparison. This article is an extension of an earlier unpublished technical report [25] and includes a longer explanation of ATAM and LDA, more technical detail such as the Gibbs sampling update equations, and more experimental comparisons between various approaches than any of our previous studies on this subject.

 

 


Via Plus91
No comment yet.
Scooped by Rémy TESTON
January 27, 2015 5:10 AM
Scoop.it!

Patients et praticiens plébiscitent la médecine connectée

Patients et praticiens plébiscitent la médecine connectée | Buzz e-sante | Scoop.it
S'ils sont une très large majorité à considérer qu'il s'agit d'une véritable opportunité, seuls 5 % se sont déjà vu recommander l'une de ces technologies par leur médecin.
No comment yet.
Scooped by Rémy TESTON
January 27, 2015 3:36 AM
Scoop.it!

e-Santé 2015 : focus sur les dernières tendances dans la Silicon Valley | L'Atelier : Accelerating Business

No comment yet.
Scooped by Rémy TESTON
January 26, 2015 4:53 AM
Scoop.it!

1001Pharmacies.com dresse le palmarès des villes françaises pour les achats e-santé — Silver Economie

1001Pharmacies.com dresse le palmarès des villes françaises pour les achats e-santé — Silver Economie | Buzz e-sante | Scoop.it
No comment yet.
Scooped by Rémy TESTON
January 26, 2015 4:46 AM
Scoop.it!

Samsung travaille sur un casque capable de prévenir un AVC

Samsung travaille sur un casque capable de prévenir un AVC | Buzz e-sante | Scoop.it
Le C Lab de Samsung veut mettre l'observation de l'activité du cerveau à la portée du grand public, et développe un casque capable de donner l'alerte avant un accident vasculaire cérébral.
No comment yet.
Rescooped by Rémy TESTON from Santé, eSanté, mSanté, santé numérique, Quantified Self et télémédecine... Toute l'actualité sur la santé de demain (en français)
January 26, 2015 4:32 AM
Scoop.it!

Données publiques de santé : l’Assurance maladie organise son Hackathon - 23/01/2015 - Actu - Le Moniteur des pharmacies.fr

Données publiques de santé : l’Assurance maladie organise son Hackathon - 23/01/2015 - Actu - Le Moniteur des pharmacies.fr | Buzz e-sante | Scoop.it
En partenariat avec la Mission Etalab, qui coordonne l’action des services de l’Etat et de ses établissements publics pour faciliter la réutilisation

Via Celine Sportisse
No comment yet.
Scooped by Rémy TESTON
January 26, 2015 3:06 AM
Scoop.it!

Bientôt un accélérateur e-santé à Toulouse, quartier des Carmes

Bientôt un accélérateur e-santé à Toulouse, quartier des Carmes | Buzz e-sante | Scoop.it
La Mêlée, l'association fédératrice des acteurs de l'économie numérique en Midi-Pyrénées.
No comment yet.
Scooped by Rémy TESTON
January 25, 2015 2:58 PM
Scoop.it!

Man 3-D prints his wife's tumour to help acquire a life-saving diagnosis

Man 3-D prints his wife's tumour to help acquire a life-saving diagnosis | Buzz e-sante | Scoop.it

3D designer Michael Balzer converted 2D MRI scans into a 3D model, 3D printed it, and circulated the print among specialists to secure a life-saving tumour diagnosis for his wife.

No comment yet.
Scooped by Rémy TESTON
January 23, 2015 3:26 AM
Scoop.it!

FrenchMedicine : service de téléconsultation médicale pour expatriés

FrenchMedicine : service de téléconsultation médicale pour expatriés | Buzz e-sante | Scoop.it
Un nouveau service de téléconsultation médicale pour expatriés et francophones a récemment été lancé : FrenchMedicine. Découverte. Lorsque l'on vit dans un pays étranger, il n'est pas toujours évid...
No comment yet.
Scooped by Rémy TESTON
January 22, 2015 5:15 AM
Scoop.it!

JIM.fr - Oui à la santé connectée !

JIM.fr - Oui à la santé connectée ! | Buzz e-sante | Scoop.it
No comment yet.
Scooped by Rémy TESTON
January 21, 2015 2:16 PM
Scoop.it!

Bientôt votre check-up santé au volant de votre voiture

Bientôt votre check-up santé au volant de votre voiture | Buzz e-sante | Scoop.it
D’ici deux ans, des systèmes sophistiqués installés dans les habitacles des voitures et connectés à Internet feront passer des check up santé aux conducteurs.
No comment yet.
Scooped by Rémy TESTON
January 20, 2015 11:46 AM
Scoop.it!

La réalité virtuelle dans la poche

La réalité virtuelle dans la poche | Buzz e-sante | Scoop.it
No comment yet.
Scooped by Rémy TESTON
January 20, 2015 7:26 AM
Scoop.it!

Addictions : un portail internet dédié aux acteurs de santé - Addictions

Intervenir-addictions.fr a pour objectif d'aider les professionnels de santé à repérer des patients souffrant d'addictions, à évaluer leur situation et à décider vers qui les orienter.
No comment yet.
Rescooped by Rémy TESTON from Pharma Hub
January 27, 2015 7:43 AM
Scoop.it!

Digital dawn: Online interactions with MDs leading to more prescripts

Digital dawn: Online interactions with MDs leading to more prescripts | Buzz e-sante | Scoop.it
Emails, webinars, and automated sales calls are three digital interactions that doctors are becoming comfortable with—and increasingly responding to by writing a prescription.

Via Philippe Marchal
No comment yet.
Rescooped by Rémy TESTON from Santé, eSanté, mSanté, santé numérique, Quantified Self et télémédecine... Toute l'actualité sur la santé de demain (en français)
January 27, 2015 4:24 AM
Scoop.it!

Inovarion, le boîtier qui suit votre métabolisme | FFTELECOMS

Inovarion, le boîtier qui suit votre métabolisme | FFTELECOMS | Buzz e-sante | Scoop.it

Via Celine Sportisse
No comment yet.
Scooped by Rémy TESTON
January 27, 2015 3:33 AM
Scoop.it!

Diabete gourmand : application mobile pour l'alimentation des diabétiques

Diabete gourmand : application mobile pour l'alimentation des diabétiques | Buzz e-sante | Scoop.it
Le laboratoire Bayer Diabetes Care met à disposition des patients diabétiques une nouvelle application mobile pour calculer les glucides et les valeurs nutritionnelles des repas : Diabète Gourmand....
No comment yet.
Scooped by Rémy TESTON
January 26, 2015 4:52 AM
Scoop.it!

Camille Freisz, au service de la santé 2.0

Camille Freisz, au service de la santé 2.0 | Buzz e-sante | Scoop.it
La cofondatrice de Valwin déploie des solutions numériques pour les pharmaciens et les patients. Une première étape pour cette entrepreneure de 30 ans, qui veut injecter de nouvelles technos dans le suivi médical.
No comment yet.
Rescooped by Rémy TESTON from Quantified Self, Data Science, Digital Health, Personal Analytics, Big Data
January 26, 2015 4:35 AM
Scoop.it!

How Technology Will Eat Medicine

How Technology Will Eat Medicine | Buzz e-sante | Scoop.it
How Technology Will Eat Medicine

Via JP DOUMENG
No comment yet.
Scooped by Rémy TESTON
January 26, 2015 4:31 AM
Scoop.it!

Quand les applications se mettent au service des déficients visuels | L'Atelier : Accelerating Business

La dernière des applications à destination des personnes visuellement déficientes se nomme Be My Eyes. Elle permet de connecter malvoyants et volontaires à travers la caméra du smartphone.
No comment yet.
Scooped by Rémy TESTON
January 26, 2015 3:02 AM
Scoop.it!

Infographie : les cardiologues face au digital

Infographie : les cardiologues face au digital | Buzz e-sante | Scoop.it
Le CESSIM a publié, en partenariat avec Ipsos, les résultats de son baromètre annuel sur les usages digitaux des professionnels de santé. Focus sur les cardiologues en infographie. La nouvelle édit...
No comment yet.
Scooped by Rémy TESTON
January 23, 2015 3:29 AM
Scoop.it!

IVG : nouveau site gouvernemental sur l'IVG, e-sante.fr

IVG : nouveau site gouvernemental sur l'IVG, e-sante.fr | Buzz e-sante | Scoop.it
Concernant l’avortement, même s’il s’agit d’une possibilité connue de tous, l’information pour les femmes en situation de grossesse non désirée manque souvent de précision. C’est d’autant plus dommageable que l’affolement peut prédominer et les empêcher de réagir d’une manière adaptée. Un site Internet vient donc d’être mis en place par le gouvernement afin d’aider les femmes souhaitant se renseigner sur les possibilités d’IVG : www.sante.gouv.fr/ivg
No comment yet.
Scooped by Rémy TESTON
January 22, 2015 5:33 AM
Scoop.it!

Applications de santé (1/3) : que captent les capteurs ? « InternetActu.net

Applications de santé (1/3) : que captent les capteurs ? « InternetActu.net | Buzz e-sante | Scoop.it
InternetActu.net
No comment yet.
Scooped by Rémy TESTON
January 22, 2015 5:14 AM
Scoop.it!

Vigipen : seringue connectée pour patients diabétiques

Vigipen : seringue connectée pour patients diabétiques | Buzz e-sante | Scoop.it
La société suisse Vigilant a présenté lors du CES à Las Vegas début janvier une seringue connectée pour les diabétiques : Vigipen. Découverte. Dans notre société d'aujourd'hui, le nombre de diabéti...
No comment yet.
Scooped by Rémy TESTON
January 21, 2015 3:15 AM
Scoop.it!

PagesJaunesDoc : service pour prendre en ligne ses rendez-vous médicaux

PagesJaunesDoc : service pour prendre en ligne ses rendez-vous médicaux | Buzz e-sante | Scoop.it
La société PagesJaunes lance un nouveau portail de prise de rendez-vous médicaux auprès des professionnels de santé : PagesJaunesDoc. Découverte. Déjà présent sur le créneau de la prise de rendez-v...
No comment yet.
Scooped by Rémy TESTON
January 20, 2015 11:37 AM
Scoop.it!

Une interface sans fil cerveau-machine dédiée aux handicapés | L'Atelier: Disruptive innovation

Des chercheurs américains sont parvenus à élaborer une interface sans fil qui pourrait permettre aux handicapés de contrôler ordinateurs, chaises roulantes et autres objets par la pensée.
No comment yet.