ArticleLiterature Review

Using Social Media Analysis to Study Population Dietary Behaviours: A Scoping

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

Background: The rapid adoption and sustained use of social media globally has provided researchers with access to unprecedented quantities of low-latency data at minimal costs. This may be of particular interest to nutrition research as food is frequently posted about and discussed on social media platforms. This scoping review investigates the ways in which social media is being used to understand population food consumption, attitudes, and behaviours. Methods: The peer-reviewed literature was searched from 2003 to 2021 using four electronic databases. Results: The review identified 71 eligible studies from 25 countries. Two thirds (n=47) were published within the last five years. The United States had the highest research output (31%, n=22) and Twitter was the most used platform (41%, n=29). A diverse range of dataset sizes were used, with some studies relying on manual techniques to collect and analyse data while others required the use of advanced software technology. Most studies were conducted by disciplines outside health with only two studies (3%) conducted by nutritionists. Conclusion: It appears the development of methodological and ethical frameworks as well as partnerships between experts in nutrition and information technology may be required to advance the field in nutrition research. Moving beyond traditional methods of dietary data collection may prove social media as a useful adjunct to inform recommended dietary practices and food policies. This article is protected by copyright. All rights reserved.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

ResearchGate has not been able to resolve any citations for this publication.
Article
Full-text available
Reporting standards, such as PRISMA aim to ensure that the methods and results of systematic reviews are described in sufficient detail to allow full transparency. Flow diagrams in evidence syntheses allow the reader to rapidly understand the core procedures used in a review and examine the attrition of irrelevant records throughout the review process. Recent research suggests that use of flow diagrams in systematic reviews is poor and of low quality and called for standardised templates to facilitate better reporting in flow diagrams. The increasing options for interactivity provided by the Internet gives us an opportunity to support easy‐to‐use evidence synthesis tools, and here we report on the development of a tool for the production of PRISMA 2020‐compliant systematic review flow diagrams. We developed a free‐to‐use, Open Source R package and web‐based Shiny app to allow users to design PRISMA flow diagrams for their own systematic reviews. Our tool allows users to produce standardised visualisations that transparently document the methods and results of a systematic review process in a variety of formats. In addition, we provide the opportunity to produce interactive, web‐based flow diagrams (exported as HTML files), that allow readers to click on boxes of the diagram and navigate to further details on methods, results or data files. We provide an interactive example here; https://prisma-flowdiagram.github.io/. We have developed a user‐friendly tool for producing PRISMA 2020‐compliant flow diagrams for users with coding experience and, importantly, for users without prior experience in coding by making use of Shiny (https://estech.shinyapps.io/prisma_flowdiagram/). This free‐to‐use tool will make it easier to produce clear and PRISMA 2020‐compliant systematic review flow diagrams. Significantly, users can also produce interactive flow diagrams for the first time, allowing readers of their reviews to smoothly and swiftly explore and navigate to further details of the methods and results of a review. We believe this tool will increase use of PRISMA flow diagrams, improve the compliance and quality of flow diagrams, and facilitate strong science communication of the methods and results of systematic reviews by making use of interactivity. We encourage the systematic review community to make use of the tool, and provide feedback to streamline and improve their usability and efficiency.
Article
Full-text available
This paper presents the report of a social media analytics (SMA) review. The review conducted to find out the methods and tools used in social media analytics, types of social media platforms which the SMA are performed and the field which SMA has been performed. Social media contains a lot of user uploaded data in different formats like text, images, photos, video etc. These large volumes of data are converted in meaningful information which can be understood using different methods and tools which are called social media analytics. A literature review of articles published between 2010-2020 has been conducted using articles obtained from reputable databases IEEE Xplore, ACM digital, Emerald insight, Springer Link and Science direct. A number of 44 articles have been selected for review from 110 retrieved papers. The paper has been reviewed according to the study objectives. The study found that SMA tools and techniques which have been used are sentiment analysis, youtube analytics, visible intelligence, IBM Watson tool and predictive models. The social media platforms which were mostly used are twitter, facebook, youtube, trip advisor and blogs. SMA has been observed in different fields like agriculture, politics, health, social and business sector.
Article
Full-text available
The Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) statement, published in 2009, was designed to help systematic reviewers transparently report why the review was done, what the authors did, and what they found. Over the past decade, advances in systematic review methodology and terminology have necessitated an update to the guideline. The PRISMA 2020 statement replaces the 2009 statement and includes new reporting guidance that reflects advances in methods to identify, select, appraise, and synthesise studies. The structure and presentation of the items have been modified to facilitate implementation. In this article, we present the PRISMA 2020 27-item checklist, an expanded checklist that details reporting recommendations for each item, the PRISMA 2020 abstract checklist, and the revised flow diagrams for original and updated reviews.
Article
Full-text available
The Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) statement, published in 2009, was designed to help systematic reviewers transparently report why the review was done, what the authors did, and what they found. Over the past decade, advances in systematic review methodology and terminology have necessitated an update to the guideline. The PRISMA 2020 statement replaces the 2009 statement and includes new reporting guidance that reflects advances in methods to identify, select, appraise, and synthesise studies. The structure and presentation of the items have been modified to facilitate implementation. In this article, we present the PRISMA 2020 27-item checklist, an expanded checklist that details reporting recommendations for each item, the PRISMA 2020 abstract checklist, and the revised flow diagrams for original and updated reviews.
Article
Full-text available
Background As social media are increasingly used worldwide, more and more scientists are relying on them for their health-related projects. However, social media features, methodologies, and ethical issues are unclear so far because, to our knowledge, there has been no overview of this relatively young field of research. Objective This scoping review aimed to provide an evidence map of the different uses of social media for health research purposes, their fields of application, and their analysis methods. Methods We followed the scoping review methodologies developed by Arksey and O’Malley and the Joanna Briggs Institute. After developing search strategies based on keywords (eg, social media, health research), comprehensive searches were conducted in the PubMed/MEDLINE and Web of Science databases. We limited the search strategies to documents written in English and published between January 1, 2005, and April 9, 2020. After removing duplicates, articles were screened at the title and abstract level and at the full text level by two independent reviewers. One reviewer extracted data, which were descriptively analyzed to map the available evidence. Results After screening 1237 titles and abstracts and 407 full texts, 268 unique papers were included, dating from 2009 to 2020 with an average annual growth rate of 32.71% for the 2009-2019 period. Studies mainly came from the Americas (173/268, 64.6%, including 151 from the United States). Articles used machine learning or data mining techniques (60/268) to analyze the data, discussed opportunities and limitations of the use of social media for research (59/268), assessed the feasibility of recruitment strategies (45/268), or discussed ethical issues (16/268). Communicable (eg, influenza, 40/268) and then chronic (eg, cancer, 24/268) diseases were the two main areas of interest. Conclusions Since their early days, social media have been recognized as resources with high potential for health research purposes, yet the field is still suffering from strong heterogeneity in the methodologies used, which prevents the research from being compared and generalized. For the field to be fully recognized as a valid, complementary approach to more traditional health research study designs, there is now a need for more guidance by types of applications of social media for health research, both from a methodological and an ethical perspective. International Registered Report Identifier (IRRID) RR2-10.1136/bmjopen-2020-040671
Article
Full-text available
COVID-19-related online fake news poses a threat to Indian public health. In response, this study seeks to understand the five important features of COVID-19-related social media fake news by analyzing 125 Indian fake news. The analysis produces five major findings based on five research questions. First, the seven themes of fake news are health, religiopolitical, political, crime, entertainment, religious, and miscellaneous. Health-related fake news (67.2%) is on the top of the list that includes medicine, medical and healthcare facilities, viral infection, and doctor-patient issues. Second, the seven types of fake news contents are text, photo, audio, video, text and photo, text and video, and text and photo and video. More fake news takes the form of text and video (47.2%). Third, online media produces more fake news (94.4%) than mainstream media (5.6%). More interestingly, four social media platforms: Twitter, Facebook, WhatsApp, and YouTube, produce most of the fake news. Fourth, relatively more fake news has international connections (54.4%) as the COVID-19 pandemic is a global phenomenon. Fifth, most of the COVID-19-related fake news is negative (63.2%) which could be a real threat to public health. These results may contribute to the academic understanding of social media fake news during the present and future health-crisis period. This paper concludes by stating some limitations regarding the data source and results, as well as provides a few suggestions for further research.
Article
Full-text available
Unprecedented public engagement with social media has provided viable and culturally relevant platforms for application in sexual health interventions, yet there are concerns that methods for evaluating engagement in these interventions have not kept pace with their implementation. More recently, the rise of social media analytics (SMA) and online marketing has spawned the development of analytic tools that boast promise for such a task. In this paper, we review a sample of the most popular of these tools, paying particular attention to: (1) the social media platforms that can be analyzed; (2) analytic capabilities; and (3) measures of engagement. We follow this with a review of sexual health intervention studies that apply these tools in evaluation efforts. Our findings suggest that these tools have numerous analytic capabilities that would be useful for evaluating interventions more efficiently. However, in nearly all cases, the tools we reviewed alone would not be sufficient to fully grasp engagement dynamics, as they need to be complemented with additional tools for textual analysis and social network analysis. Therefore, we consider this fertile ground for future collaborations between software developers and behavioral health scientists to develop more comprehensive analytic platforms with applications for public health research.
Preprint
Full-text available
COVID-19-related online fake news poses a threat to Indian public health. In response, this study seeks to understand the five important features of COVID-19-related social media fake news by analyzing 125 Indian fake news. The analysis produces five major findings based on five research questions. First, the seven themes of fake news are health, religiopolitical, political, crime, entertainment, religious, and miscellaneous. Health-related fake news (67.2%) is on the top of the list that includes medicine, medical and healthcare facilities, viral infection, and doctor-patient issues. Second, the seven types of fake news contents are text, photo, audio, video, text and photo, text and video, and text and photo and video. More fake news takes the form of text and video (47.2%). Third, online media produces more fake news (94.4%) than mainstream media (5.6%). More interestingly, four social media platforms: Twitter, Facebook, WhatsApp, and YouTube, produce most of the fake news. Fourth, relatively more fake news has international connections (54.4%) as the COVID-19 pandemic is a global phenomenon. Fifth, most of the COVID-19-related fake news is negative (63.2%) which could be a real threat to public health. These results may contribute to the academic understanding of social media fake news during the present and future health-crisis period. This paper concludes by stating some limitations regarding the data source and results, as well as provides a few suggestions for further research.
Article
Full-text available
The outbreak of Corona Virus Disease 2019 (COVID-19) is a grave global public health emergency. Nowadays, social media has become the main channel through which the public can obtain information and express their opinions and feelings. This study explored public opinion in the early stages of COVID-19 in China by analyzing Sina-Weibo (a Twitter-like microblogging system in China) texts in terms of space, time, and content. Temporal changes within one-hour intervals and the spatial distribution of COVID-19-related Weibo texts were analyzed. Based on the latent Dirichlet allocation model and the random forest algorithm, a topic extraction and classification model was developed to hierarchically identify seven COVID-19-relevant topics and 13 sub-topics from Weibo texts. The results indicate that the number of Weibo texts varied over time for different topics and sub-topics corresponding with the different developmental stages of the event. The spatial distribution of COVID-19-relevant Weibo was mainly concentrated in Wuhan, Beijing-Tianjin-Hebei, the Yangtze River Delta, the Pearl River Delta, and the Chengdu-Chongqing urban agglomeration. There is a synchronization between frequent daily discussions on Weibo and the trend of the COVID-19 outbreak in the real world. Public response is very sensitive to the epidemic and significant social events, especially in urban agglomerations with convenient transportation and a large population. The timely dissemination and updating of epidemic-related information and the popularization of such information by the government can contribute to stabilizing public sentiments. However, the surge of public demand and the hysteresis of social support demonstrated that the allocation of medical resources was under enormous pressure in the early stage of the epidemic. It is suggested that the government should strengthen the response in terms of public opinion and epidemic prevention and exert control in key epidemic areas, urban agglomerations, and transboundary areas at the province level. In controlling the crisis, accurate response countermeasures should be formulated following public help demands. The findings can help government and emergency agencies to better understand the public opinion and sentiments towards COVID-19, to accelerate emergency responses, and to support post-disaster management.
Article
Full-text available
In this study the evolution of Big Data (BD) and Data Science (DS) literatures and the relationship between the two are analyzed by bibliometric indicators that help establish the course taken by publications on these research areas before and after forming concepts. We observe a surge in BD publications along a gradual increase in DS publications. Interestingly, a new publications course emerges combining the BD and DS concepts. We evaluate the three literature streams using various bibliometric indicators including research areas and their origin, central journals, the countries producing and funding research and startup organizations, citation dynamics, dispersion and author commitment. We find that BD and DS have differing academic origin and different leading publications. Of the two terms, BD is more salient, possibly catalyzed by the strong acceptance of the pre-coordinated term by the research community, intensive citation activity, and also, we observe, by generous funding from Chinese sources. Overall, DS literature serves as a theory-base for BD publications.
Article
Full-text available
The impact of computational technologies and the worldwide use of Internet entails a theoretical and methodological challenge for social scientists, considering the purpose of observing, interpreting and explaining human and social behaviour. Today, the digital environment seems to be an adequate space for this exploration and the emergence of the Web 2.0 offers common people the possibility of expressing and sharing their opinions on a daily basis. Due to the ubiquity of technology, Internet and social media in people’s lives, socialization and its expressiveness have changed. If this is the case, the means to measure the perceptions, opinions and judgements of citizens should also change. The immense quantity of data available to be analysed today poses a challenge for the traditional scientific model. In this sense, it could be necessary for social research to move towards the analysis of the web and consider the potential predictive capacity of digital demoscopy. A new field of study has opened, with interest in exploring the predictive capacity of social media in electoral contexts. As a research group comprised by linguists, communication experts and engineers we explored the predictive potential of social media in three national elections that took place in Chile during 2017. Our objective was to explore a methodological design that allows predicting the result of political elections through the use of inductive algorithms and the automatic processing of messages with political opinion in social media. Through computational intelligence, we were able to follow, collect and analyse millions of tweets, and to improve our forecast each time. Our learning based on empirical research was fundamental to improve our procedures and to refine our variables and, thus, improve our prediction.
Article
Full-text available
Food marketing influences eating preferences and choices, especially among adolescents, contributing to the rise of overweight, obesity, and other chronic health disorders. Recent social media advancements have provided food marketers with platforms to reach out to many in more personal and authentic ways as compared to classical media advertising. Such personalized and borderless social media platforms allow marketers to easily use owned, paid, and earned (word-of –mouth) marketing strategies, including paid and non-paid influencers to reach younger target audiences. This study therefore aims to explore food messages adolescents (12–18 years old) encounter on social media, and assess these messages for their sources, the presence of core and non-core food, and the marketing strategies employed. To attain an in-depth understanding of the food messages that adolescents are continuously exposed to, we carried out a diary study with 21 Flemish adolescents who took screenshots of food images they encountered on their social media platforms for the duration of one week. A quantitative and qualitative content analysis of 611 images revealed that adolescents are mostly exposed to messages of non-core (67% of images) and branded (49% of images) food, often (49% of images) presented in association with a social context such as hanging around with friends, eating at restaurants and celebrating with food. Adolescents often encounter branded food images through peers and social media influencers, the majority of which are part of earned (49% of branded images) or paid (40% of branded images) media food marketing. This research provides an in-depth understanding of the social media messages that adolescents encounter on a daily basis and sheds light on food norms typically communicated on social media by marketers, peers, and influencers. Study findings highlight prominent social media food messages that should be tested for their persuasiveness, providing insights for future research that aims to assess the effects of social media food marketing on adolescents. Based on the study findings, we call for relevant policy actions that address current social media marketing strategies targeted at adolescents.
Article
Full-text available
Background Health researchers are increasingly using social media in a professional capacity, and the applications of social media for health researchers are vast. However, there is currently no published evidence synthesis of the ways in which health researchers use social media professionally, and uncertainty remains as to how best to harness its potential. Objective This scoping review aimed to explore how social media is used by health researchers professionally, as reported in the literature. Methods The scoping review methodology guided by Arksey and O’Malley and Levac et al was used. Comprehensive searches based on the concepts of health research and social media were conducted in MEDLINE, EMBASE, CINAHL, PsycINFO, ERIC, and Web of Science databases, with no limitations applied. Articles were screened at the title and abstract level and at full text by two reviewers. One reviewer extracted data that were analyzed descriptively to map the available evidence. Results A total of 8359 articles were screened at the title and abstract level, of which 719 were also assessed at full text for eligibility. The 414 articles identified for inclusion were published in 278 different journals. Studies originated from 31 different countries, with the most prevalent being the United States (52.7% [218/414]). The health discipline of the first authors varied, with medicine (33.3% [138/414]) being the most common. A third of the articles covered health generally, with 61 health-specific topics. Papers used a range of social media platforms (mean 1.33 [SD 0.7]). A quarter of the articles screened reported on social media use for participant recruitment (25.1% [104/414]), followed by practical ways to use social media (15.5% [64/414]), and use of social media for content analysis research (13.3% [55/414]). Articles were categorized as celebratory (ie, opportunities for engagement, 72.2% [299/414]), contingent (ie, opportunities and possible limitations, 22.7% [94/414]) and concerned (ie, potentially harmful, 5.1% [21/414]). Conclusions Health researchers are increasingly publishing on their use of social media for a range of professional purposes. Although most of the sentiment around the use of social media in health research was celebratory, the uses of social media varied widely. Future research is needed to support health researchers to optimize their social media use.
Conference Paper
Full-text available
Monitoring population-level changes in diet could be useful for education and for implementing interventions to improve health. Research has shown that data from social media sources can be used for monitoring dietary behavior.We propose a scrape-by-location methodology to create food image datasets from Instagram posts. We used it to collect 3.56 million images over a period of 20 days in March 2019. We also propose a scrape-by-keywords methodology and used it to scrape -30,000 images and their captions of 38 Kenyan food types.We publish two datasets of 104,000 and 8,174 image/caption pairs, respectively. With the first dataset, Kenya104K, we train a Kenyan Food Classifier, called KenyanFC, to distinguish Kenyan food from non-food images posted in Kenya.We used the second dataset, KenyanFood13, to train a classifier Kenyan-FTR, short for Kenyan Food Type Recognizer, to recognize 13 popular food types in Kenya. The KenyanFTR is a multimodal deep neural network that can identify 13 types of Kenyan foods using both images and their corresponding captions. Experiments show that the average top-1 accuracy of KenyanFC is 99% over 10,400 tested Instagram images and of KenyanFTR is 81% over 8,174 tested data points. Ablation studies show that three of the 13 food types are particularly difficult to categorize based on image content only and that adding analysis of captions to the image analysis yields a classifier that is 9 percent points more accurate than a classifier that relies only on images. Our food trend analysis revealed that cakes and roasted meats were the most popular foods in photographs on Instagram in Kenya in March 2019.
Article
Full-text available
With the amplification of social media platforms, the importance of social media analytics has exponentially increased for many brands and organizations across the world. Tracking and analyzing the social media data has been contributing as a success parameter for such organizations, however, the data is being poorly harnessed. Therefore, the ethical implications of social media analytics need to be identified and explored for both the organizations and targeted users of social media data. The present work is an exploratory study to identify the various techno-ethical concerns of social media engagement, as well as social media analytics. The impact of these concerns on the individuals, organizations, and society as a whole are discussed. Ethical engagement for the most common social media platforms has been outlined with a number of specific examples to understand the prominent techno-ethical concerns. Both the individual and organizational perspectives have been taken into account to identify the implications of social media analytics.
Article
Full-text available
Scoping reviews, a type of knowledge synthesis, follow a systematic approach to map evidence on a topic and identify main concepts, theories, sources, and knowledge gaps. Although more scoping reviews are being done, their methodological and reporting quality need improvement. This document presents the PRISMA-ScR (Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews) checklist and explanation. The checklist was developed by a 24-member expert panel and 2 research leads following published guidance from the EQUATOR (Enhancing the QUAlity and Transparency Of health Research) Network. The final checklist contains 20 essential reporting items and 2 optional items. The authors provide a rationale and an example of good reporting for each item. The intent of the PRISMA-ScR is to help readers (including researchers, publishers, commissioners, policymakers, health care providers, guideline developers, and patients or consumers) develop a greater understanding of relevant terminology, core concepts, and key items to report for scoping reviews.
Article
Full-text available
Aim This article examines whether social media postings dealing with cancer and so-called ‘functional foods’ simply reflect a fashionable subject or are based on scientific evidence. Methods The first step consisted of an analysis of a sample of Pins published on Pinterest. The second consisted of an analysis to determine whether the content of the Pins was based on scientific research. Results From a set of 507 Pins on cancer, we found 204 that also dealt with food. We selected 75 Pins representing different foods and we identified about 80,000 scientific articles on cancer and food indexed in PubMed. Conclusion We concluded that material published on Pinterest has some correlation with the scientific literature.
Article
Full-text available
Since an ever-increasing part of the population makes use of social media in their day-today lives, social media data is being analysed in many different disciplines. The social media analytics process involves four distinct steps, data discovery, collection, preparation, and analysis. While there is a great deal of literature on the challenges and difficulties involving specific data analysis methods, there hardly exists research on the stages of data discovery, collection, and preparation. To address this gap, we conducted an extended and structured literature analysis through which we identified challenges addressed and solutions proposed. The literature search revealed that the volume of data was most often cited as a challenge by researchers. In contrast, other categories have received less attention. Based on the results of the literature search, we discuss the most important challenges for researchers and present potential solutions. The findings are used to extend an existing framework on social media analytics. The article provides benefits for researchers and practitioners who wish to collect and analyse social media data.
Article
Full-text available
There is a large body of research on utilizing online activity as a survey of political opinion to predict real world election outcomes. There is considerably less work, however, on using this data to understand topic-specific interest and opinion amongst the general population and specific demographic subgroups, as currently measured by relatively expensive surveys. Here we investigate this possibility by studying a full census of all Twitter activity during the 2012 election cycle along with the comprehensive search history of a large panel of Internet users during the same period, highlighting the challenges in interpreting online and social media activity as the results of a survey. As noted in existing work, the online population is a non-representative sample of the offline world (e.g., the U.S. voting population). We extend this work to show how demographic skew and user participation is non-stationary and difficult to predict over time. In addition, the nature of user contributions varies substantially around important events. Furthermore, we note subtle problems in mapping what people are sharing or consuming online to specific sentiment or opinion measures around a particular topic. We provide a framework, built around considering this data as an imperfect continuous panel survey, for addressing these issues so that meaningful insight about public interest and opinion can be reliably extracted from online and social media data.
Article
Full-text available
Recent years have seen an increase in the amount of statistics describing different phenomena based on “Big Data.” This term includes data characterized not only by their large volume, but also by their variety and velocity, the organic way in which they are created, and the new types of processes needed to analyze them and make inference from them. The change in the nature of the new types of data, their availability, and the way in which they are collected and disseminated is fundamental. This change constitutes a paradigm shift for survey research. There is great potential in Big Data, but there are some fundamental challenges that have to be resolved before its full potential can be realized. This report provides examples of different types of Big Data and their potential for survey research; it also describes the Big Data process, discusses its main challenges, and considers solutions and research needs.
Article
Full-text available
This article aims to provide a model with which to measure the degree of corporate social media use or, in other words, the extent to which companies are exploiting the potentialities of single or multiple social media platforms. This is, however, explicitly different from using metrics to assess the success of social media activities, as it is purely measuring how intensively a pre-defined group of social media is utilised, taking into account the frequency of social media activity by the brand as well as the related user reactions. The degree of corporate social media use helps companies and market researchers analyse single brands or companies and compare them with other brands, competitors or industry averages. The degree of corporate social media use is a useful indicator, which should be combined with social media metrics in order to draw better conclusions about where to increase or intensify social media activities.
Article
Full-text available
The ever-growing volume of brand-related conversations on social media platforms has captivated the attention of academics and practitioners, as the analysis of those conversations promises to offer unparalleled insight into consumers’ emotions. This article takes a step back from the hype, and investigates the vulnerabilities related to the analysis of social media data concerning consumers’ sentiment. A review of the literature indicates that the form, focus, source and context of the communication may negatively impact on the analyst’s ability to identify sentiment polarity and emotional state. Likewise, the selection of analytical tool, the creation of codes, and the classification of the data, adversely affect the researcher’s ability to accurately assess the sentiment expressed in a social media conversation. Our study of Twitter conversations about coffee shows low levels of agreement between manual and automated analysis, which is of grave concern given the popularity of the latter in consumer research.
Article
Full-text available
Automatic monitoring of Adverse Drug Reactions (ADRs), defined as adverse patient outcomes caused by medications, is a challenging research problem that is currently receiving significant attention from the medical informatics community. In recent years, user-posted data on social media, primarily due to its sheer volume, has become a useful resource for ADR monitoring. Research using social media data has progressed using various data sources and techniques, making it difficult to compare distinct systems and their performances. In this paper, we perform a methodical review to characterize the different approaches to ADR detection/extraction from social media, and their applicability to pharmacovigilance. In addition, we present a potential systematic pathway to ADR monitoring from social media.
Article
Full-text available
This paper is written for (social science) researchers seeking to analyze the wealth of social media now available. It presents a comprehensive review of software tools for social networking media, wikis, really simple syndication feeds, blogs, newsgroups, chat and news feeds. For completeness, it also includes introductions to social media scraping, storage, data cleaning and sentiment analysis. Although principally a review, the paper also provides a methodology and a critique of social media tools. Analyzing social media, in particular Twitter feeds for sentiment analysis, has become a major research and business activity due to the availability of web-based application programming interfaces (APIs) provided by Twitter, Facebook and News services. This has led to an ‘explosion’ of data services, software tools for scraping and analysis and social media analytics platforms. It is also a research area undergoing rapid change and evolution due to commercial pressures and the potential for using social media data for computational (social science) research. Using a simple taxonomy, this paper provides a review of leading software tools and how to use them to scrape, cleanse and analyze the spectrum of social media. In addition, it discussed the requirement of an experimental computational environment for social media research and presents as an illustration the system architecture of a social media (analytics) platform built by University College London. The principal contribution of this paper is to provide an overview (including code fragments) for scientists seeking to utilize social media scraping and analytics either in their research or business. The data retrieval techniques that are presented in this paper are valid at the time of writing this paper (June 2014), but they are subject to change since social media data scraping APIs are rapidly changing.
Article
Full-text available
Purpose – The electronic social media such as Twitter, Facebook, MySpace, etc. have become a major form of communication, and the expression of attitudes and opinions, for the general public. Recently, they have also become a source of data for market researchers. This paper aims to provide a critical look at the advantages and limitations of such an approach to understanding brand perceptions and attitudes in the market place. Although the social media provide a wealth of data for automated content analyses, this review questions the validity and reliability of this research approach, and concludes that social media monitoring (SMM) is a poor substitute for in‐depth qualitative research which has many advantages and benefits. Design/methodology/approach – The paper presents a detailed, systematic comparison of various research approaches. These include well‐established methods and recent inventions which are in use to explore and understand consumer behaviour and attitudes. Particular attention is given to the analysis of spontaneous consumer attitudes as expressed through the social media and also in qualitative research interviews. Findings – This analysis concludes that there are three critical features which differentiate qualitative research (as practised in IDIs and group discussions) from SMM. These are: the direct, interactive dialogue or conversation between consumers and researchers; the facility to “listen” and attend to the (sometimes unspoken) underlying narrative which connects consumers' needs and aspirations, personal goals and driving forces to behaviour and brand choice; and the dynamic, interactive characteristics of the interview that achieve a meeting of minds to produce a shared understanding. Philosophically, it is this “conversation” that gives qualitative research its validity and authenticity which makes it superior to SMM. Originality/value – This review questions the validity and reliability of the SMM, and concludes that it is a poor substitute for in‐depth qualitative research which has many advantages and benefits.
Article
Full-text available
The concept of Social Media is top of the agenda for many business executives today. Decision makers, as well as consultants, try to identify ways in which firms can make profitable use of applications such as Wikipedia, YouTube, Facebook, Second Life, and Twitter. Yet despite this interest, there seems to be very limited understanding of what the term “Social Media” exactly means; this article intends to provide some clarification. We begin by describing the concept of Social Media, and discuss how it differs from related concepts such as Web 2.0 and User Generated Content. Based on this definition, we then provide a classification of Social Media which groups applications currently subsumed under the generalized term into more specific categories by characteristic: collaborative projects, blogs, content communities, social networking sites, virtual game worlds, and virtual social worlds. Finally, we present 10 pieces of advice for companies which decide to utilize Social Media.
Article
Full-text available
Qualitative research methods require transparency to ensure the ‘trustworthiness’ of the data analysis. The intricate processes of organizing, coding and analyzing the data are often rendered invisible in the presentation of the research findings, which requires a ‘leap of faith’ for the reader. Computer assisted data analysis software can be used to make the research process more transparent, without sacrificing rich, interpretive analysis by the researcher. This article describes in detail how one software package was used in a poststructural study to link and code multiple forms of data to four research questions for fine-grained analysis. This description will be useful for researchers seeking to use qualitative data analysis software as an analytic tool.
Article
Objective Social media analytics (SMA) has a track record in business research. The utilisation in nutrition research is unknown, despite social media being populated with real-time, eating behaviours. This rapid review aimed to explore the use of SMA in nutrition research with the investigation of dietary behaviours. Design The review was conducted according to rapid review guidelines by WHO and the National Collaborating Centre for Methods and Tools. Five databases of peer-reviewed, English language studies were searched using the keywords ‘social media’ in combination with ‘data analytics’ and ‘food’ or ‘nutrition’ and screened for those with general population health using SMA on public domain, social media data between 2014-2020. Results The review identified 34 studies involving SMA in the investigation of dietary behaviours. Nutrition topics included population nutrition health investigations, alcohol consumption, dieting and eating out of the home behaviours. All studies involved content analysis with evidence of surveillance and engagement. Twitter was predominant with data sets in tens of million. SMA tools were observed in data discovery, collection and preparation, but less so in data analysis. Approximately a third of the studies involved interdisciplinary collaborations with health representation and only two studies involved nutrition disciplines. Less than a quarter of studies obtained formal human ethics approval. Conclusions SMA in nutrition research with the investigation of dietary behaviours is emerging, nevertheless, if consideration is taken with technological capabilities and ethical integrity, the future shows promise at a broad population census level and as a scoping tool or complementary, triangulation instrument.
Article
Social media allows for the exploration of online discussions of health issues outside of traditional health spaces. Twitter is one of the largest social media platforms that allows users to post short comments (i.e., tweets). The unrestricted access to opinions and a large user base makes Twitter a major source for collection and quick dissemination of some health information. Health organizations, individuals, news organizations, businesses, and a host of other entities discuss health issues on Twitter. However, the enormous number of tweets presents challenges to those who seek to improve their knowledge of health issues. For instance, it is difficult to understand the overall sentiment on a health issue or the central message of the discourse. For Twitter to be an effective tool for health promotion, stakeholders need to be able to understand, analyze, and appraise health information and discussions on this platform. The purpose of this paper is to examine how a visual analytic study can provide insight into a variety of health issues on Twitter. Visual analytics enhances the understanding of data by combining computational models with interactive visualizations. Our study demonstrates how machine learning techniques and visualizations can be used to analyze and understand discussions of health issues on Twitter. In this paper, we report on the process of data collection, analysis of data, and representation of results. We present our findings and discuss the implications of this work to support the use of Twitter for health promotion.
Article
Consumer beliefs play an important role in explaining consumer behavior. This exploratory study aims at building an inventory of consumer beliefs about organic food. To reach this objective, we conducted a content analysis of online comments about organic food posted on news websites and forums in German-speaking countries (n = 1094) and the United States (n = 1069). Such user-generated content has emerged as an abundant source of insight for consumer research, although very little has been exploited in organic food consumption research. The main result of this study is a comprehensive category system of 65 organic food beliefs and their relative frequencies. The category system reflects the large variety of beliefs and their differing salience within and across the two regions studied. We discuss the relevance of our category system for future survey, experimental, and textual research, as well as for marketing practitioners and policy-makers.
Article
Taking ecological perspectives to overweight and obesity, the current study applies data mining approach to examine the association between information and social environments and regional prevalence of overweight and obesity. In particular, we focus on online search and social media data since the increasing popularity of location-based geo-targeting could be an influential source of regional differences in health information and social environment. In Study 1, we calculated the correlation between regional overweight and obesity rates with regional Google searches for a time period of 12 years (2004 to 2016). The findings showed that in regions with high overweight and obesity rates, people were looking for and obtaining information on weight-loss and diet;, but in regions with low overweight and obesity rates, people were looking for and obtaining information on fitness services and facilities. In Study 2, we analyzed and compared 4010 tweets from Houston, a city with a high overweight and obesity rate, and 3281 tweets from San Diego, a city with a low overweight and obesity rate. The tweets were collected from August 2015 to August of 2016. We analyzed the textual content of tweets by word frequency analysis and topic modeling. The findings suggest that San Diego has a social environment that focuses on fitness and combining exercising with dieting. In contrast, Houston’s social environment emphasizes dieting. The implication of these findings is that health practitioners should push a paradigm shift to a stronger focus on “healthy life” (combining exercising and dieting) in regions with high overweight and obesity rates.
Article
In "Social Media, e-Health, and Medical Ethics," in this issue of the Hastings Center Report, Mélanie Terrasse, Moti Gorin, and Dominic Sisti address and suggest recommendations for several ethical issues central to the systematic ethical analysis of the effects of social media on clinical practice, health services research, and public health. The topic is as timely as it is important: social media data collected by device and web applications are constantly increasing and might have both individual and public health benefits. The authors focus their analysis primarily on the health care context. Yet the implications of the intersection of social media data and research warrant focused consideration, as even the most thorough ethical analysis in the clinical context is not necessarily directly applicable in the research context. While many ethical issues are present in both settings, the research context poses new challenges and calls for consideration of distinct factors. In particular, because the legal framework is less protective in research, critical ethical analysis of the research-specific issues and considerations is essential to the ethical conduct of research using social media data as well as to the design and operation of social media device and web applications themselves.
Article
Background: Support following bariatric surgery is critical. Access to bariatric support groups is sometimes challenging, leading people to seek support on social media platforms like Facebook. Given the ubiquity of recommendations solicited and provided on Facebook regarding nutrition and bariatric surgery, understanding the content and accuracy of these posts is important. Objectives: The primary aim of the current study was to describe the content of nutrition-related information sought on bariatric Facebook support groups/pages. A secondary aim was to evaluate the accuracy of this content. Setting: Integrated multispecialty health system. Methods: An iterative content analysis process was conducted and resulted in identification of 8 primary coding themes. Additionally, three registered dietitians with extensive experience in bariatric surgery and obesity treatment examined posts that provided nutritional recommendations to determine accuracy. Results: Members sought advice regarding products and practices to assist in achieving nutritional guidelines most commonly (35%). Over half of the posts contained inaccurate content or information that was too ambiguous to determine accuracy; 7% of posts were found to be inaccurate or inconsistent with ASMBS nutrition guidelines and expert RD opinions, 22% of posts were found to contain both accurate and inaccurate information, and 24% of posts were considered too ambiguous and required more context to determine the accuracy. Conclusions: Results highlight the need for bariatric programs to provide greater nutrition education support to patients postoperatively, and to provide caution about the inconsistent nature of some nutrition-related content found on Facebook bariatric support groups.
Article
While big data offer exciting opportunities to address questions about social behavior, studies must not abandon traditionally important considerations of social science research such as data representativeness and sampling biases. Many big data studies rely on traces of people’s behavior on social media platforms such as opinions expressed through Twitter posts. How representative are such data? Whose voices are most likely to show up on such sites? Analyzing survey data about a national sample of American adults’ social network site usage, this article examines what user characteristics are associated with the adoption of such sites. Findings suggest that several sociodemographic factors relate to who adopts such sites. Those of higher socioeconomic status are more likely to be on several platforms suggesting that big data derived from social media tend to oversample the views of more privileged people. Additionally, Internet skills are related to using such sites, again showing that opinions visible on these sites do not represent all types of people equally. The article cautions against relying on content from such sites as the sole basis of data to avoid disproportionately ignoring the perspectives of the less privileged. Whether business interests or policy considerations, it is important that decisions that concern the whole population are not based on the results of analyses that favor the opinions of those who are already better off.
Article
Advances in computer science and computational linguistics have yielded new, and faster, computational approaches to structuring and analyzing textual data. These approaches perform well on tasks like information extraction, but their ability to identify complex, socially constructed, and unsettled theoretical concepts—a central goal of sociological content analysis—has not been tested. To fill this gap, we compare the results produced by three common computer-assisted approaches—dictionary, supervised machine learning (SML), and unsupervised machine learning—to those produced through a rigorous hand-coding analysis of inequality in the news (N = 1,253 articles). Although we find that SML methods perform best in replicating hand-coded results, we document and clarify the strengths and weaknesses of each approach, including how they can complement one another. We argue that content analysts in the social sciences would do well to keep all these approaches in their toolkit, deploying them purposefully according to the task at hand.
Conference Paper
In the traditional world, marketing studies managed to employ various techniques to explore customers' consensual experiences toward products with limited information available. The uses of surveys, focus groups or regular individual interviews are some of the frequently used methods by marketers. We are now entering in the era of Big Data. The explosion and profusion of the unprecedented scale of heterogeneous data available in this new era allow us to acquire further insights and knowledge about the market for improving the quality of products. In this paper, we present a Social Media-based Product Improvement Framework (SM-PIF) which is capable of deriving recommendations for product improvement and subsequently increase the product's market competitiveness. The recommendation generated by the SM-PIF is expected to be more accurate and less biased than traditional methods due to its "Big Data" nature.
Article
Although there is a growing body of research on social media, only few studies have considered organic products. Therefore, this study mapped the diffusion path of the social media resources for organic products in Mexico and South Korea through Twitter and compared the contents of tweets about organic products in terms of their semantic and hyperlink networks using webometric methods. The results indicate that for organic products, Koreans sent tweets much more frequently than Mexicans. Mexican tweets focused on basic food products in street markets, whereas Korean tweets highlighted promotions and firms, revealing the corporatist structure of its economy. In both cases, the findings support Twitter as a useful tool for Word-of-Mouth Communication on the online environment, among product consumers, and between consumers and enterprises.
Conference Paper
Using social media analytics tools, Radian6 and Visible Technologies, Purdue Homeland Security Institute (PHSI) researchers were able to monitor, capture and analyze publicly posted online information pertaining to the Super Bowl XLVI. The study collected and analyzed data regarding the public's perceptions of the Super Bowl XLVI marketing campaign, as well as Indianapolis' hospitality, accommodations, and safety. Data was collected from three different platforms: Facebook, Twitter, and blogs. The results of the study provided insights into public sentiment, public dialogue regarding specific citywide events, and trending social media topics associated with each topic's keyword analysis. In our research we further explored the potential usage and application of social media analytics tools within local government and found that social media analytics can be of great value for the government in both special events and routine activities. Major applications of social media analytics as well as research questions and issues worth exploring in the future, including improving information flow and analytics for routine operations, are discussed.
Article
This paper focuses on scoping studies, an approach to reviewing the literature which to date has received little attention in the research methods literature. We distinguish between different types of scoping studies and indicate where these stand in relation to full systematic reviews. We outline a framework for conducting a scoping study based on our recent experiences of reviewing the literature on services for carers for people with mental health problems. Where appropriate, our approach to scoping the field is contrasted with the procedures followed in systematic reviews. We emphasize how including a consultation exercise in this sort of study may enhance the results, making them more useful to policy makers, practitioners and service users. Finally, we consider the advantages and limitations of the approach and suggest that a wider debate is called for about the role of the scoping study in relation to other types of literature reviews.
Article
This exploratory study describes the virtual socialization, behaviors, and attitudes being promoted in one community of food bloggers. Two months of entries from 45 blogs created by young women belonging to a photography-based food blogging community were analyzed and coded using a qualitative approach. Analysis revealed widespread group practices as well as the promotion of attitudes and behaviors associated with dietary restraint. The present study highlights the need for further research using food-blogging communities, and concludes with a cautionary note about blogs as sources of health information in view of the consequences of dietary restraint.
Article
To determine the prevalence of and associations among displayed risk behavior information that suggests sexual behavior, substance use, and violence in a random sample of the self-reported 18-year-old adolescents' publicly accessible MySpace Web profiles. Cross-sectional study using content analysis of Web profiles between July 15 and September 30, 2007. www.MySpace.com. A total of 500 publicly available Web profiles of self-reported 18-year-olds in the United States. Prevalence and associations among displayed health risk behaviors, including sexual behavior, substance use, or violence, on Web profiles. A total of 270 (54.0%) profiles contained risk behavior information: 120 (24.0%) referenced sexual behaviors, 205 (41.0%) referenced substance use, and 72 (14.4)% referenced violence. Female adolescents were less likely to display violence references (odds ratio [OR], 0.3; 95% confidence interval [CI], 0.15-0.6). Reporting a sexual orientation other than "straight" was associated with increased display of references to sexual behavior (OR, 4.48; 95% CI, 1.27-15.98). Displaying church or religious involvement was associated with decreased display of all outcomes (sex: OR, 0.32; 95% CI, 0.12-0.86; substance use: OR, 0.38; 95% CI, 0.19-0.79; violence: OR, 0.12; 95% CI, 0.02-0.87; any risk factor: OR, 0.36; 95% CI, 0.19-0.7). Displaying sport or hobby involvement was associated with decreased references to violence (OR, 0.27; 95% CI, 0.09-0.79) and any risk factor (OR, 0.46; 95% CI, 0.27-0.79). Adolescents frequently display risk behavior information on public Web sites. Further study is warranted to explore the validity of such information and the potential for using social networking Web sites for health promotion.
Social media to social media analytics
  • Kumar V
An experimental analysis of clustering sentiments for opinion mining. Proceedings of the 2017 International Conference on Machine Learning and Soft Computing
  • Babu A
A “fitness” theme may mitigate regional prevalence of overweight and obesity: evidence from Google Search and Tweets
  • B Liang
  • Y Wang
  • MA Tsou
An experimental analysis of clustering sentiments for opinion mining. Proceedings of the 2017 International Conference on Machine Learning and Soft Computing
  • A Babu
  • S Kumari
  • K Kamakshaiah