A vast amount of media‐related text data is generated daily in the form of social media posts, news stories or academic articles. These text data provide opportunities for researchers to analyse and ...understand how substance‐related issues are being discussed. The main methods to analyse large text data (content analyses or specifically trained deep‐learning models) require substantial manual annotation and resources. A machine‐learning approach called ‘zero‐shot learning’ may be quicker, more flexible and require fewer resources. Zero‐shot learning uses models trained on large, unlabelled (or weakly labelled) data sets to classify previously unseen data into categories on which the model has not been specifically trained. This means that a pre‐existing zero‐shot learning model can be used to analyse media‐related text data without the need for task‐specific annotation or model training. This approach may be particularly important for analysing data that is time critical. This article describes the relatively new concept of zero‐shot learning and how it can be applied to text data in substance use research, including a brief practical tutorial.
Abstract
Background
Music is an integral part of our lives and is often played in public places like restaurants. People exposed to music that contained alcohol-related lyrics in a bar scenario ...consumed significantly more alcohol than those exposed to music with less alcohol-related lyrics. Existing methods to quantify alcohol exposure in song lyrics have used manual annotation that is burdensome and time intensive. In this paper, we aim to build a deep learning algorithm (LYDIA) that can automatically detect and identify alcohol exposure and its context in song lyrics.
Methods
We identified 673 potentially alcohol-related words including brand names, urban slang, and beverage names. We collected all the lyrics from the Billboard’s top-100 songs from 1959 to 2020 (N = 6110). We developed an annotation tool to annotate both the alcohol-relation of the word (alcohol, non-alcohol, or unsure) and the context (positive, negative, or neutral) of the word in the song lyrics.
Results
LYDIA achieved an accuracy of 86.6% in identifying the alcohol-relation of the word, and 72.9% in identifying its context. LYDIA can distinguish with an accuracy of 97.24% between the words that have positive and negative relation to alcohol; and with an accuracy of 98.37% between the positive and negative context.
Conclusion
LYDIA can automatically identify alcohol exposure and its context in song lyrics, which will allow for the swift analysis of future lyrics and can be used to help raise awareness about the amount of alcohol in music.
Highlights
Developed a deep learning algorithm (LYDIA) to identify alcohol words in songs.
LYDIA achieved an accuracy of 86.6% in identifying alcohol-relation of the words.
LYDIA’s accuracy in identifying positive, negative, or neutral context was 72.9%.
LYDIA can automatically provide evidence of alcohol in millions of songs.
This can raise awareness of harms of listening to songs with alcohol words.
Aims
To describe the range of effects experienced due to the drinking of people respondents know and analyze risk and protective factors for harm from the drinking of partners and household members, ...other relatives and friends and co‐workers.
Design, setting and participants
Surveys of 2574 participants' experiences were obtained from two samples: 1000 people responded to random digitally dialled Australian mobile calls and 1574 participants responded from the Life in AustraliaTM panel survey.
Measurements
Respondents were asked whether they had been negatively affected in the previous 12 months by the drinking of persons they knew who were ‘a heavy drinker or drank a lot sometimes’ and the nature of these harms. Weighted logistic regressions were used to analyze differences in rates of key negative outcomes from known others' drinking by gender, age and socio‐economic status.
Findings
Almost two thirds 60.2%; 95% confidence interval (CI) = 57.7%–62.7% of participants reported having heavy drinkers in their lives and 21.8% (95% CI = 19.8%–23.9%) reported being negatively affected by the drinking of people they knew well in some way. Participants reported a gamut of effects, including, most commonly, adverse social effects: having to transport relatives and friends who had been drinking, role failure and faults, being emotionally hurt or neglected, serious arguments, family problems, having to care for drinkers and verbal abuse. Less commonly, respondents reported physical or sexual harm, property damage, financial stress and threats from others' drinking. Women (odds ratio = 1.49; 95% CI = 1.13–1.95), younger people, rural, Australian‐born (vs. respondents born overseas in non‐English speaking countries) and more frequent drinkers were more likely to report harm from a drinker they knew than their counterparts after adjusting for other variables in the model.
Conclusions
Australians appear to be commonly adversely affected by the drinking of people they know. Harms from known drinkers are more likely to be experienced by women than men, particularly from the people they live with and other relatives.
Introduction
The aim of this study was to: (i) determine the feasibility of using ecological momentary assessment to collect data from Australian Football League (AFL) fans; (ii) explore pre‐game, ...during‐game and post‐game consumption patterns of AFL fans; and (iii) explore the social and setting‐related factors associated with risky single occasion drinking (5+ drinks) among AFL fans.
Methods
Thirty‐four participants completed up to 10 ecological momentary assessment surveys before, during and after 63 AFL games (n = 437 completed surveys). Surveys collected data about their drinking, and their social and environmental milieu (e.g., location, company). Binary logistic regression analyses clustered by participant identified which game‐day characteristics were associated with higher odds of risky single occasion drinking. Significant differences between pre‐game, during‐game and post‐game drinking on social and environmental factors were explored using pairwise comparisons.
Results
Risky single occasion drinking was more likely when games began in the early‐afternoon (1–3 pm) than late‐afternoon (3–6 pm), when participants watched the game at a stadium or pub compared to home, and when participants watched the game with friends compared to family. Pre‐drinking was more likely before night games and post‐drinking was more likely after day games. Drinking during the game was heavier when watching the game at a pub and when watching with a combined group of friends and family.
Discussion and Conclusions
Preliminary findings suggest that social and contextual factors matter in the way alcohol is consumed while watching AFL games. These findings require further investigation in larger samples.
Exposure to alcohol content in media increases alcohol consumption and related harm. With exponential growth of media content, it is important to use algorithms to automatically detect and quantify ...alcohol exposure. Foundation models such as Contrastive Language-Image Pretraining (CLIP) can detect alcohol exposure through Zero-Shot Learning (ZSL) without any additional training. In this paper, we evaluated the ZSL performance of CLIP against a supervised algorithm called Alcoholic Beverage Identification Deep Learning Algorithm Version-2 (ABIDLA2), which is specifically trained to recognise alcoholic beverages in images, across three tasks. We found ZSL achieved similar performance compared to ABIDLA2 in two out of three tasks. However, ABIDLA2 outperformed ZSL in a fine-grained classification task in which determining subtle differences among alcoholic beverages (including containers) are essential. We also found that phrase engineering is essential for improving the performance of ZSL. To conclude, like ABIDLA2, ZSL with little phrase engineering can achieve promising performance in identifying alcohol exposure in images. This makes it easier for researchers, with little or no programming background, to implement ZSL effectively to obtain insightful analytics from digital media. Such analytics can assist researchers and policy makers to propose regulations that can prevent alcohol exposure and eventually prevent alcohol consumption.
Sustainability Risk Management Anderson, Dan R.; Anderson, Kenneth E.
Risk management and insurance review,
Spring 2009, Letnik:
12, Številka:
1
Journal Article
Recenzirano
This article features a panel discussion on sustainability risk management organized by Dan R Anderson for the American Risk and Insurance Association 2007 annual meeting. The moderator, Mr. Dan ...Anderson, is the Leslie P Schulz Professor of Risk Management and Insurance at the University of Wisconsin-Madison School of Business and author of Corporate Survival: The Critical Importance of Sustainability Risk Management. PUBLICATION ABSTRACT
The search for historical justice has become one of the defining features of the late twentieth and early twenty-first centuries. So has the consensus about the need to remember the violence of past ...injustices and its victims. The search for justice is closely related to a focus on remembrance: the striving for justice relies on memories of injustices, and the public remembering of past wrongs is increasingly considered one crucial means of redressing such wrongs. This focus section brings together authors from a variety of disciplinary backgrounds in the humanities and social sciences, ranging from anthropology to law, and from cultural studies to political science. Focusing on post-conflict societies in Africa (Morocco, Rwanda), Asia (Nepal), Latin America (Argentina, Peru, Uruguay) and the Pacific (Solomon Islands), the papers explore aspects of the work of memory in attempts to redress past wrongs and make the present inhabitable. This introduction also extends some of the themes that connect the seven individual papers.
Understanding the prevalence of alcohol references in music and their impact on alcohol drinking behavior is important given the increased accessibility to daily music listening with the ...proliferation of smart devices. In this review, we estimate the pooled prevalence of alcohol references in music and its association with drinking behavior. Systematic searches were conducted across four major databases (MEDLINE, PsycINFO, EMBASE, and CINHAL). Articles were selected following duplicate checking, title and screening, and full‐text review. Studies reporting the prevalence of alcohol‐referencing music and/or investigating its association with drinking behavior were included. Pooled prevalence with 95% confidence intervals (CIs) were computed using a random effects model. Of 1007 articles identified, 26 met inclusion criteria and 23 studies comprising 12,224 songs were eligible for meta‐analysis. The overall pooled prevalence of alcohol references in music (including lyrics and videos) was 24.0% (95% CI: 19.0%–29.0%). The pooled prevalence was 22.0% (95% CI: 16.0%–29.0%) for only lyrics, 25.0% (95% CI: 18.0%–33.0%) for only the visual elements of music videos, and 29.0% (95% CI: 21.0%–38.0%) for both the lyrical content and the visual components. Only three studies assessed the relationship between listening to music with alcohol references and drinking behavior, and all three reported a positive association. Whereas almost a quarter of all songs included references to alcohol, public health preventive measures are needed to reduce alcohol exposure from music. Future research is needed to understand fully the effect of music with alcohol references on drinking behavior.
We conducted a meta‐analysis to estimate the prevalence of alcohol references in music and its association with drinking behaviour. The overall pooled prevalence of alcohol references in music was 24.0%. However, the pooled prevalence varied across different music content like lyrics only (22.0%), visual elements of music videos only (25.0%), and both lyrics and visual elements (29.0%). Only three studies examined the association between listening to music with alcohol reference and drinking behaviours, all reporting a positive association.
The search for historical justice has become one of the defining features of the late twentieth and early twenty-first centuries. So has the consensus about the need to remember the violence of past ...injustices and its victims. The search for justice is closely related to a focus on remembrance: the striving for justice relies on memories of injustices, and the public remembering of past wrongs is increasingly considered one crucial means of redressing such wrongs. This focus section brings together authors from a variety of disciplinary backgrounds in the humanities and social sciences, ranging from anthropology to law, and from cultural studies to political science. Focusing on post-conflict societies in Africa (Morocco, Rwanda), Asia (Nepal), Latin America (Argentina, Peru, Uruguay) and the Pacific (Solomon Islands), the papers explore aspects of the work of memory in attempts to redress past wrongs and make the present inhabitable. This introduction also extends some of the themes that connect the seven individual papers.