Diet, Weight loss, Fitness, and Health related Image Sharing using Twitter: an Observation Study

Park, Albert; Li, Chuqin; Bowling, Jessamyn; Ge, Yaorong; Dulin, Michael

doi:10.1109/bibm49941.2020.9313194

Cited by 5 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most frequent inaccurate prediction came from identifying the degree of healthiness of food images as the classifier inaccurately classified as healthy for definitively healthy or as unhealthy for definitively unhealthy food images. The performance of our image classifier is better than the F1 scores reported by other deep CNN approaches that are applied in public health informatics research [ 6 , 16 , 29 , 33 ]. We were able to improve the performance by transfer features from a neural network with a greater number of layers, ResNet 152.…”

Section: Discussionmentioning

confidence: 72%

“…Twitter has been demonstrated as a good data source for tracking public health issues like influenza [ 35 , 36 ] seasonal allergies [ 36 ], cholera outbreaks [ 37 ], mental health [ 37 , 38 , 39 ] and behaviors like excessive and unhealthy food consumption [ 6 ]. However, these studies mainly used text as the only data source.…”

Section: Discussionmentioning

confidence: 99%

“…However, these studies mainly used text as the only data source. Although a growing number of Twitter users are sending out images, image analysis has not been the main focus of most previous public health studies using Twitter, in part due to the difficulty of accurately processing images [ 6 , 19 , 35 ]. Although images are often accompanied by captions, oftentimes these captions are not descriptive of the images themselves [ 16 ].…”

Section: Discussionmentioning

confidence: 99%

“…In their study, Park et al suggested that the general public’s everyday habits and beliefs concerning health can be observed using social media data [ 6 ]. In fact, food marketing on social media has been suggested to influence the intake of high-energy and low-nutrient foods such as fried foods and candy [ 7 ].…”

Section: Introductionmentioning

confidence: 99%

“…More than 1.1 million obesity-related tweeted images were processed by a very deep Visual Geometry Group (VGG16) model, and it did not perform well. These results suggest the need for a fine-tuned image classification tool for social media images [ 6 ]. This is why we opted to adopt the ResNet-152 for training.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Healthy vs. Unhealthy Food Images: Image Classification of Twitter Images

Oduru

Jordan

Park

2022

IJERPH

Self Cite

View full text Add to dashboard Cite

Obesity is a modern public health problem. Social media images can capture eating behavior and the potential implications to health, but research for identifying the healthiness level of the food image is relatively under-explored. This study presents a deep learning architecture that transfers features from a 152 residual layer network (ResNet) for predicting the level of healthiness of food images that were built using images from the Google images search engine gathered in 2020. Features learned from the ResNet 152 were transferred to a second network to train on the dataset. The trained SoftMax layer was stacked on top of the layers transferred from ResNet 152 to build our deep learning model. We then evaluate the performance of the model using Twitter images in order to better understand the generalizability of the methods. The results show that the model is able to predict the images into their respective classes, including Definitively Healthy, Healthy, Unhealthy and Definitively Unhealthy at an F1-score of 78.8%. This finding shows promising results for classifying social media images by healthiness, which could contribute to maintaining a balanced diet at the individual level and also understanding general food consumption trends of the public.

show abstract

Section: Discussionmentioning

confidence: 72%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Healthy vs. Unhealthy Food Images: Image Classification of Twitter Images

Oduru

Jordan

Park

2022

IJERPH

Self Cite

View full text Add to dashboard Cite

show abstract

Sharing healthy lifestyle information on social media during the COVID-19 pandemic: a moderated mediation model

Balamoorthy

Chandra

2022

Journal of Marketing Communications

View full text Add to dashboard Cite

Ifood: Development and usability study of a social media-based applet for dietary monitoring

Lan,

Xu,

Guo

et al. 2023

DIGITAL HEALTH

View full text Add to dashboard Cite

Background Dietary monitoring is critical to maintaining human health. Social media platforms are widely used for daily recording and communication for individuals’ diets and activities. The textual content shared on social media offers valuable resources for dietary monitoring. Objective This study aims to describe the development of iFood, an applet providing personal dietary monitoring based on social media content, and validate its usability, which will enable efficient personal dietary monitoring. Methods The process of the development and validation of iFood is divided into four steps: Diet datasets construction, diet record and analysis, diet monitoring applet design, and diet monitoring applet usability assessment. The diet datasets were constructed with the data collected from Weibo, Meishijie, and diet guidelines, which will be used as the basic knowledge for further model training in the phase of diet record and analysis. Then, the friendly user interface was designed to link users with backend functions. Finally, the applet was deployed as a WeChat applet and 10 users from the Beijing Union Medical College have been recruited to validate the usability of iFood. Results Three dietary datasets, including User Visual-Textual Dataset, Dietary Information Expansion Dataset, and Diet Recipe Dataset have been constructed. The performance of 4 models for recognizing diet and fusing unimodality data was 40.43%(dictionary-based model), 18.45%(rule-based model), 59.95%(Inception-ResNet-v2), and 51.38% (K-nearest neighbor), respectively. Furthermore, we have designed a user-friendly interface for the iFood applet and conducted a usability assessment, which resulted in an above-average usability score. Conclusions iFood is effective for managing individual dietary behaviors through its seamless integration with social media data. This study suggests that future products could utilize social media data to promote healthy lifestyles.

show abstract

Diet, Weight loss, Fitness, and Health related Image Sharing using Twitter: an Observation Study

Cited by 5 publications

References 17 publications

Healthy vs. Unhealthy Food Images: Image Classification of Twitter Images

Healthy vs. Unhealthy Food Images: Image Classification of Twitter Images

Sharing healthy lifestyle information on social media during the COVID-19 pandemic: a moderated mediation model

Ifood: Development and usability study of a social media-based applet for dietary monitoring

Contact Info

Product

Resources

About