Towards tracking and analysing regional alcohol consumption patterns in the UK through the use of social media
Open Access
- 23 June 2014
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 220-228
Abstract
Permission to make digital or hard copies of all or part of this work for personal or\ud classroom use is granted without fee provided that copies are not made or distributed\ud for profit or commercial advantage and that copies bear this notice and the full citation\ud on the first page. Copyrights for components of this work owned by others than the\ud author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or\ud republish, to post on servers or to redistribute to lists, requires prior specific permission\ud and/or a fee. Request permissions from permissions@acm.org.Monitoring rates of alcohol consumption across the UK is\ud a timely problem due to ever-increasing drinking levels [36].\ud This has led to calls from public services (e.g. police and\ud health services) to assess the effect it is having on people and\ud society. Current research methods that are utilised to assess\ud consumption patterns are costly, time consuming, and do\ud not supply sufficiently detailed results. This is because they\ud look at snapshots of individuals' drinking patterns, which\ud rely on generalised usage patterns, and post consumption re-\ud call. In this paper we look into the use of social media such as\ud Twitter (a popular micro blogging site) to monitor the rate\ud of alcohol consumption in regions across the UK by introducing the Social Media Alcohol Index (SMAI). By looking at\ud the variation in term usage, and treating the social network\ud as a spatio-temporal self-reporting sense-network, we aim\ud to discover variation in drinking patterns on both local and\ud national levels within the UK. This study used 31.6 million\ud tweets collected over a 6 week period, and used the Health\ud & Social Care Information Centre (HSCIC) weekly alcohol\ud consumption pattern as a ground truth. High correlations\ud between the ground truth and the computed SMAI (Social\ud Media Alcohol Index) were found on a national and local\ud level, along with the ability to detect variation in consumption on National holidays and celebrations at both local and\ud national levelsKeywords
Funding Information
- Digital Economy programme (EP/G037582/1)
This publication has 16 references indexed in Scilit:
- The Parable of Google Flu: Traps in Big Data AnalysisScience, 2014
- Social media as a measurement tool of depression in populations2013
- Lightweight methods to estimate influenza rates and alcohol sales volume from Twitter messagesLanguage Resources and Evaluation, 2012
- Twitter mood predicts the stock marketJournal of Computational Science, 2011
- Pandemics in the Age of Twitter: Content Analysis of Tweets during the 2009 H1N1 OutbreakPLOS ONE, 2010
- Networks, Crowds, and Markets2010
- TwitterMonitor2010
- Detecting influenza epidemics using search engine query dataNature, 2009
- Alcohol and public healthThe Lancet, 2005
- Alcohol-related crime and disorder across urban space and time: evidence from a British cityGeoforum, 2002