Assessing Behavior Stage Progression From Social Media Data

Liu, Jiaxin; Weitzman, Elissa R.; Chunara, Rumi

doi:10.1145/2998181.2998336

Cited by 39 publications

(23 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For this study the options "never" and "yes, in the last year" were used. This selection was made contemplating the purpose of this study, taking into account the presence of factors and triggering moments for the use of substances at different times of the year, called "High-risk Time Periods", such as the new year and other holidays, 17 as well as periods in which there is an intense consumption of alcohol 18 and in summer holiday season 19 which allowed us to expand the possibilities of finding students who have had the substance use practices of interest for the present study. The ASSIST guide is also recommended for use in developing countries due to its reliability and validity.…”

Section: /11mentioning

confidence: 99%

Knowledge of the Consequences and Use of Drugs for Costa Rica University Students

Chaves

Khenti

2019

Texto contexto - enferm.

View full text Add to dashboard Cite

Objective: to determine the relationship between knowledge of consequences and drug use in undergraduate students of a university in San José, Costa Rica. Method: the cross-sectional study examines the demographic profile of the sample and the relationship between knowledge of consequences, drug use and academic performance. The study focuses on three types of drugs: alcohol, marijuana and cocaine. Three variables will be analyzed: demographic data, knowledge of consequences and use of drugs. Results: the relationship between knowledge of consequences and use of drugs was made using of the T-test. The sample had 272 students, 28.2% (n=77) of them were men and 71.4% were women (n=195). They were selected from the areas of social sciences (n=137, 50.2%), and from the area of health sciences (n=136; 49.8%). Alcohol was the most used drug (n=217, 79.8%), followed by marijuana (n=72, 26.6%) and finally cocaine (n=3, 1.1%) in the last 12 months. Conclusion: the results shown indicate that there is no significant relationship between such variables. The findings are important at the level of drug policies to support the development of new preventive strategies for drug use.Objetivo: determinar a relação entre o conhecimento das consequências e o uso de drogas em estudantes de graduação de uma universidade em San José, Costa Rica. Método: este estudo, de corte transversal, examina o perfil demográfico da amostra e a relação entre o conhecimento das consequências, o uso de drogas e o desempenho acadêmico. A pesquisa centra-se em três tipos de drogas: álcool, maconha e cocaína. Três variáveis foram analisadas: os dados demográficos, o conhecimento das consequências e o uso de drogas. Resultados: a relação entre o conhecimento das consequências e o uso de drogas foi realizada através do uso do T-test. A amostra foi composta por 272 estudantes, sendo 28,2% (n=77) homens e 71,4% mulheres (n=195); selecionados da área de ciências sociais (n=137;50,2%), e da área de ciências da saúde (n=136;49,8%). O álcool foi a droga mais utilizada (n=217;79,8%), seguida da maconha (n=72;26,6%) e, finalmente, a cocaína (n=3; 1.1%) nos últimos 12 meses. Conclusão: os resultados demostram que não existe relação significativa entre tais variáveis, e são importantes no nível das políticas de drogas para apoiar o desenvolvimento de novas estratégias preventivas para o uso de drogas.

show abstract

Section: /11mentioning

confidence: 99%

Knowledge of the Consequences and Use of Drugs for Costa Rica University Students

Chaves

Khenti

2019

Texto contexto - enferm.

View full text Add to dashboard Cite

show abstract

“…For each of the behaviors, Tweets were classified hierarchically into behavior versus not behavior related, then first person versus not first person (the person Tweeting is talking about themselves performing the action). Finally, to isolate episodes of consuming alcohol or tobacco that are linked to precise times, for each pipeline the Tweets were classified into past, present, and future following previous work identifying behavior stages from social media [53]. As we are interested in self-reported communications of behaviors linked to time, we used data from the “present” category of the last classification for further analyses in this paper.…”

Section: Data Preprocessingmentioning

confidence: 99%

“…For both behaviors, due to the low percentage of behavior-specific Tweets, as well as the nuanced differences between marijuana and tobacco, the training (labelled) data was very carefully curated and we used active learning following the approach in [53]. First, we developed a dictionary, using Internet sources such as Urban dictionary and Wikipedia as references to pre-filter Tweets that would be submitted for manual labeling, in order to increase instances of target classes.…”

Section: Data Preprocessingmentioning

confidence: 99%

See 1 more Smart Citation

High-resolution Temporal Representations of Alcohol and Tobacco Behaviors from Social Media Data

Huang

Elghafari

Relia

et al. 2017

Proc. ACM Hum.-Comput. Interact.

Self Cite

View full text Add to dashboard Cite

Understanding tobacco- and alcohol-related behavioral patterns is critical for uncovering risk factors and potentially designing targeted social computing intervention systems. Given that we make choices multiple times per day, hourly and daily patterns are critical for better understanding behaviors. Here, we combine natural language processing, machine learning and time series analyses to assess Twitter activity specifically related to alcohol and tobacco consumption and their sub-daily, daily and weekly cycles. Twitter self-reports of alcohol and tobacco use are compared to other data streams available at similar temporal resolution. We assess if discussion of drinking by inferred underage versus legal age people or discussion of use of different types of tobacco products can be differentiated using these temporal patterns. We find that time and frequency domain representations of behaviors on social media can provide meaningful and unique insights, and we discuss the types of behaviors for which the approach may be most useful.

show abstract

“…Online social communities constitute a significant presence in our lives. Researchers and practitioners are using online data to illuminate many aspects of life including health, politics and culture, based on what people post [1][2][3][4][5]. For example, some studies have focused on recipe websites and shown how food names in online recipes can be a proxy for consumption and dietary patterns of individuals [6].…”

Section: Introductionmentioning

confidence: 99%

Role of the Built and Online Social Environments on Expression of Dining on Instagram

Mhasawade

Elghafari

Duncan

et al. 2020

IJERPH

Self Cite

View full text Add to dashboard Cite

Online social communities are becoming windows for learning more about the health of populations, through information about our health-related behaviors and outcomes from daily life. At the same time, just as public health data and theory has shown that aspects of the built environment can affect our health-related behaviors and outcomes, it is also possible that online social environments (e.g., posts and other attributes of our online social networks) can also shape facets of our life. Given the important role of the online environment in public health research and implications, factors which contribute to the generation of such data must be well understood. Here we study the role of the built and online social environments in the expression of dining on Instagram in Abu Dhabi; a ubiquitous social media platform, city with a vibrant dining culture, and a topic (food posts) which has been studied in relation to public health outcomes. Our study uses available data on user Instagram profiles and their Instagram networks, as well as the local food environment measured through the dining types (e.g., casual dining restaurants, food court restaurants, lounges etc.) by neighborhood. We find evidence that factors of the online social environment (profiles that post about dining versus profiles that do not post about dining) have different influences on the relationship between a user’s built environment and the social dining expression, with effects also varying by dining types in the environment and time of day. We examine the mechanism of the relationships via moderation and mediation analyses. Overall, this study provides evidence that the interplay of online and built environments depend on attributes of said environments and can also vary by time of day. We discuss implications of this synergy for precisely-targeting public health interventions, as well as on using online data for public health research.

show abstract

Assessing Behavior Stage Progression From Social Media Data

Cited by 39 publications

References 68 publications

Knowledge of the Consequences and Use of Drugs for Costa Rica University Students

Knowledge of the Consequences and Use of Drugs for Costa Rica University Students

High-resolution Temporal Representations of Alcohol and Tobacco Behaviors from Social Media Data

Role of the Built and Online Social Environments on Expression of Dining on Instagram

Contact Info

Product

Resources

About