Journal Article10.1080/10410236.2023.2175635
How Visual Aesthetics and Calorie Density Predict Food Image Popularity on Instagram: A Computer Vision Analysis.
Muna Sharma,Yilang Peng +1 more
7
TL;DR: In this paper , the effects of visual aesthetics and calorie density of foods on audience engagement on Instagram were investigated, and it was found that visual aesthetics varied by calorie content and were more pronounced for low-calorie images.
read more
Abstract: Social media have become an important source where people are exposed to visual representations of foods. This study aims to understand what content factors contribute to the popularity of food images on Instagram. We collected 53,894 images from 90 popular food influencer accounts on Instagram over two years. Applying computer vision methods, we investigated the effects of visual aesthetics and calorie density of foods on audience engagement (i.e. likes, comments) as well as if the effects of visual aesthetics varied by calorie density. Our results showed that both visual aesthetics and calorie density were important predictors of image popularity. The use of arousing, warm colors such as red, orange, and yellow, feature complexity, and repetition predicted higher likes, whereas brightness, colorfulness, and compositional complexity acted reversely. A similar pattern was observed for comments. The calorie density of foods in images positively predicted likes and comments. Also, the effects of visual aesthetics varied by calorie content and were more pronounced for low-calorie images. Health practitioners who plan to harness the power of social media to encourage certain dietary behaviors should take visual aesthetics into account when designing persuasive messages and campaigns.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Like it, buy it? Examining the role of bookmarking in the mediation of visual appeal and purchase intent from a dual-system perspective
Youngjoon Yu,Jae-Hyeon Ahn,Dongyeon Kim,Kyuhong Park +3 more
- 01 Jan 2024
TL;DR: This study examines the role of bookmarking in mediating the relationship between visual appeal and purchase intent, finding that bookmarking fully mediates the influence of visual appeal on purchase intent, with colorfulness positively and visual complexity inversely related to visual appeal.
5
Convergence or divergence? A cross-platform analysis of climate change visual content categories, features, and social media engagement on Twitter and Instagram
Sijia Qian,Yingdan Lu,Yilang Peng,Huacen Xu +3 more
TL;DR: This study analyzes climate change visual content on Twitter and Instagram, discovering platform-specific categories, features, and engagement patterns, providing insights for climate advocacy organizations to tailor their strategies for maximum effectiveness on each platform.
5
A Computer Vision Methodology to Predict Brand Personality from Image Features
Taylor Jing Wen,Yilang Peng,Jing Yang +2 more
TL;DR: This study proposes a computer vision methodology to predict brand personality from image features, analyzing the effects of colors and visual complexity on perceived brand personality through a four-step procedure correlating visual attributes with human ratings.
2
Pixelator v2: A Novel Perceptual Image Comparison Method with LAB Colour Space and Sobel Edge Detection for Enhanced Security Analysis
Somdip Dey,Jabir Alshehabi Al-Ani,Aikaterini Bourazeri,Suman Saha,Rohit Purkait,Samuel Hill,J.W. Thompson +6 more
TL;DR: Pixelator v2 is a novel image comparison method combining LAB colour space and Sobel edge detection for enhanced security analysis, offering a more robust and nuanced approach to identifying subtle image variations, ideal for security applications like tamper detection and authentication.
Sentiment Classification of Food Influencer Content Reviews using Support Vector Machine Model through CRISP-DM Framework
Yerik Afrianto Singgalen
TL;DR: This research reveals challenges in culinary tourism marketing aligned with tourist preferences, necessitating substantial exploration of consumer sentiments related to culinary diversity through food influencer content and highlights the vital performance metrics of SVM models, both with and without SMOTE.
References
Endorsement and visual complexity in food advertising on Instagram
TL;DR: As celebrities and higher levels of visual complexity result in more favorable responses to Instagram ads, food marketers need to consider increasing visual complexity when using celebrities in advertising by adding more objects, using more colors, objects, or textures and incorporating asymmetric elements in the advertisements.
149
On the multiple effects of packaging colour on consumer behaviour and product experience in the ‘food and beverage’ and ‘home and personal care’ categories
Charles Spence,Carlos Velasco +1 more
TL;DR: A growing body of empirical research now shows that packaging color affects everything from the expected and perceived taste and flavour of food and beverage products through to the fragrance of home and personal care items.
144
Using Reports of Symptoms and Diagnoses on Social Media to Predict COVID-19 Case Counts in Mainland China: Observational Infoveillance Study.
TL;DR: This infoveillance study employs the largest, most comprehensive, and most fine-grained social media data to date to predict COVID-19 case counts in mainland China and finds that reports of symptoms and diagnosis of CO VID-19 significantly predicted daily case counts up to 14 days ahead of official statistics.
Why a ‘light’ product package should not be light blue: Effects of package colour on perceived healthiness and attractiveness of sugar- and fat-reduced products
TL;DR: In this paper, the authors used package color to make a healthy product more attractive. But, they did not consider the effect of package color on the intended message of healthy foods.
117
Using Reports of Own and Others' Symptoms and Diagnosis on Social Media to Predict COVID-19 Case Counts: Observational Infoveillance Study in Mainland China
TL;DR: Public social media data can be usefully harnessed to predict infection cases and inform timely responses, and leveraging machine learning approaches and theoretical understandings of information sharing behaviors is a promising approach to identifying true disease signals and improving the effectiveness of infoveillance.