Collection and Visualization of Dietary Behavior and Reasons for Eating Using Twitter

Abstract

BackgroundIncreasing an individual’s awareness and understanding of their dietary habits and reasons for eating may help facilitate positive dietary changes. Mobile technologies allow individuals to record diet-related behavior in real time from any location; however, the most popular software applications lack empirical evidence supporting their efficacy as health promotion tools.ObjectiveThe purpose of this study was to test the feasibility and acceptability of a popular social media software application (Twitter) to capture young adults’ dietary behavior and reasons for eating. A secondary aim was to visualize data from Twitter using a novel analytic tool designed to help identify relationships among dietary behaviors, reasons for eating, and contextual factors.MethodsParticipants were trained to record all food and beverages consumed over 3 consecutive days (2 weekdays and 1 weekend day) using their mobile device’s native Twitter application. A list of 24 hashtags (#) representing food groups and reasons for eating were provided to participants to guide reporting (eg, #protein, #mood). Participants were encouraged to annotate hashtags with contextual information using photos, text, and links. User experience was assessed through a combination of email reports of technical challenges and a 9-item exit survey. Participant data were captured from the public Twitter stream, and frequency of hashtag occurrence and co-occurrence were determined. Contextual data were further parsed and qualitatively analyzed. A frequency matrix was constructed to identify food and behavior hashtags that co-occurred. These relationships were visualized using GMap algorithmic mapping software.ResultsA total of 50 adults completed the study. In all, 773 tweets including 2862 hashtags (1756 foods and 1106 reasons for eating) were reported. Frequently reported food groups were #grains (n=365 tweets), #dairy (n=221), and #protein (n=307). The most frequently cited reasons for eating were #social (activity) (n=122), #taste (n=146), and #convenience (n=173). Participants used a combination of study-provided hash tags and their own hash tags to describe behavior. Most rated Twitter as easy to use for the purpose of reporting diet-related behavior. “Maps” of hash tag occurrences and co-occurrences were developed that suggested time-varying diet and behavior patterns.ConclusionsTwitter combined with an analytical software tool provides a method for capturing real-time food consumption and diet-related behavior. Data visualization may provide a method to identify relationships between dietary and behavioral factors. These findings will inform the design of a study exploring the use of social media and data visualization to identify relationships between food consumption, reasons for engaging in specific food-related behaviors, relevant contextual factors, and weight and health statuses in diverse populations.

Digital phenotyping and the development and delivery of health guidelines and behaviour change interventions

“…From the digital footprints left by individuals on services such as Twitter and Facebook, researchers can identify temporal and geographic patterns in a wide range of health behaviours, including smoking [9], drinking alcohol [10] and eating [11]. Specific approaches to utilizing social media data vary, from using occurrences of specified keywords (e.g.…”

Mobile Ecological Momentary Diet Assessment Methods for Behavioral Research: Systematic Review (Preprint)

“…Hingle and colleagues [56] collected 1,756 food-related hashtags via Twitter across all participants over 3 days. In Seto and colleagues' [59] 6-day study, 72 food items were reported via video per participant.…”

“…A total of 10 studies described event-contingent mEMDA methods used in nutrition-related research [52][53][54][55][56][57][58][59][60][61]. Additional approach details were extracted from other related journal articles [43,[62][63][64][65][66][67][68][69][70][71][72][73].…”

“…The remaining 5 studies used a PDA device with customized software [55,60], an Internet-based app [52,54], or social media (Twitter) [56]. All studies assessed dietary intake continuously throughout each day.…”

“…analyze the data based on a nutrient database or software [52,53,57,59]; 3 studies downloaded data from the mobile device to perform further data analysis without the use of a nutrient database or software [55,58,60]; 2 utilized output generated by non-nutrient-related software or app [54,56], and 1 automated the nutrient analysis within the study app [61]. With respect to the primary outcomes assessed, 5 studies estimated energy intake [52,53,57,58,61].…”