How clickable are your food photos?

2018-10-11
Many people view the food photos available in social media when choosing a restaurant. The attractiveness of these photos is an important factor in shaping initial impressions about a restaurant. There are some properties such as colour harmony, colour balance, and content of an image which constitutes the aesthetics of an image. Although there are several works on predicting image aesthetics, our experiments showed that the aesthetic scores and view numbers of food images are not correlated. In this work, we developed a neural network model which aims to predict the clickability of a food photo. We have created a new dataset by scraping the images and their view number information from Flickr and achieved 65% accuracy in estimating images which gets a high number of clicks

Suggestions

How useful is social feedback for learning to rank YouTube videos?
CHELARU, Sergiu; Orellana-Rodriguez, Claudia; Altıngövde, İsmail Sengör (Springer Science and Business Media LLC, 2014-09-01)
A vast amount of social feedback expressed via ratings (i.e., likes and dislikes) and comments is available for the multimedia content shared through Web 2.0 platforms. However, the potential of such social features associated with shared content still remains unexplored in the context of information retrieval. In this paper, we first study the social features that are associated with the top-ranked videos retrieved from the YouTube video sharing site for the real user queries. Our analysis considers both r...
Design guidelines for lunch box as compact home experience
Köktürk, Ceren; Kaygan, Harun; Department of Industrial Design (2016)
Turkish food culture, which is built upon a rich background, lunch boxes remain as an important product in the face of recent changes in eating habits. This study investigates the meaning and significance of lunch boxes for Turkish users and designers in the face of changing habits in food culture. The studyaims to determine the major reasons for using lunch boxes today, and define the users’ needs regarding lunch boxes in terms of design and functionality. The main research consists of three parts, which a...
Investigating the factors affecting customer engagement and the influence of customer engagement on brand loyalty in automobile online brand communities
Bayraktar, Pelin; Özkan Yıldırım, Sevgi; Department of Information Systems (2022-2-10)
The purpose of this study is to identify the factors affecting customer engagement dimensions in online brand communities (OBCs) and to investigate the intra- and inter-relationships between engagement and loyalty dimensions. In this study, quantitative and qualitative analyses were combined in order to gain an in depth understanding of the issue. Quantitative data were collected via questionnaires from 721 automobile OBC members and analyzed using structural equation modelling (SEM). Then, a semi-structure...
Empirical investigation on the determinants of organic food purchasing behavior
Dinç Cavlak, Özge; Özdemir, Özlem; Department of Political Science and Public Administration (2019)
The main motivation of this thesis is to reveal the determinants of organic food purchasing behavior of individuals by improving a psychological model and try to elicit individuals’ willingness to pay estimates for each attribute of organic foods in an experimental setting. In the first essay, we aim to reveal the determinants of organic food purchasing behavior within the Theory of Planned Behavior framework, and the basic model is extended by incorporating food safety concern, health consciousness, trust,...
TRUST-AWARE LOCATION RECOMMENDATION IN LOCATION-BASED SOCIAL NETWORKS
Cantürk, Deniz; Karagöz, Pınar; Department of Computer Engineering (2021-8-9)
Users can share their location with other social network users through location-embedded information in LBSNs (Location-Based Social Network). LBSNs contain useful resources, such as user check-in activities, for building a personalized recommender system. Trust in social networks is another important concept that has been integrated into a recommendation system in various settings. In this thesis, we propose two novel techniques for location recommendation, TLoRW and SgWalk, to improve recommendation perfo...
Citation Formats
H. Kumdakçı, T. Taşkaya Temizel, and A. Temizel, “How clickable are your food photos?,” presented at the GPU Technology Conference Europe (2018), Munich, Germany, 2018, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/83697.