On the predictability of the popularity of online recipes

Christoph Trattner, Dominik Moesslang, David Elsweiler

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Popularity prediction has been studied in diverse online contexts with demonstrable practical, sociological and technical benefit. Here, we add to the popularity prediction literature by studying the popularity of recipes on two large and well visited online recipe portals (Allrecipes.com, USA and Kochbar.de, Germany). Our analyses show differences between the platforms in terms of how the recipes are interacted with and categorized, as well as in the content of the food and its nutritional properties. For both datasets, we were able to show correlations between recipe features and proxies for popularity, which allow popularity of dishes to be predicted with some accuracy. The trends were more prominent in the Kochbar.de dataset, which was mirrored in the results of the prediction task experiments.

LanguageEnglish
Article number20
JournalEPJ Data Science
Volume7
Issue number1
DOIs
StatusPublished - 1 Dec 2018

Fingerprint

Predictability
Prediction
Experiment
Experiments

Keywords

  • Food
  • Online recipes
  • Popularity

ASJC Scopus subject areas

  • Modelling and Simulation
  • Computer Science Applications
  • Computational Mathematics

Cite this

On the predictability of the popularity of online recipes. / Trattner, Christoph; Moesslang, Dominik; Elsweiler, David.

In: EPJ Data Science, Vol. 7, No. 1, 20, 01.12.2018.

Research output: Contribution to journalArticleResearchpeer-review

Trattner, Christoph ; Moesslang, Dominik ; Elsweiler, David. / On the predictability of the popularity of online recipes. In: EPJ Data Science. 2018 ; Vol. 7, No. 1.
@article{61c4178a369347c5ad3bdf3978708ed5,
title = "On the predictability of the popularity of online recipes",
abstract = "Popularity prediction has been studied in diverse online contexts with demonstrable practical, sociological and technical benefit. Here, we add to the popularity prediction literature by studying the popularity of recipes on two large and well visited online recipe portals (Allrecipes.com, USA and Kochbar.de, Germany). Our analyses show differences between the platforms in terms of how the recipes are interacted with and categorized, as well as in the content of the food and its nutritional properties. For both datasets, we were able to show correlations between recipe features and proxies for popularity, which allow popularity of dishes to be predicted with some accuracy. The trends were more prominent in the Kochbar.de dataset, which was mirrored in the results of the prediction task experiments.",
keywords = "Food, Online recipes, Popularity",
author = "Christoph Trattner and Dominik Moesslang and David Elsweiler",
year = "2018",
month = "12",
day = "1",
doi = "10.1140/epjds/s13688-018-0149-5",
language = "English",
volume = "7",
journal = "EPJ Data Science",
issn = "2193-1127",
publisher = "SpringerOpen",
number = "1",

}

TY - JOUR

T1 - On the predictability of the popularity of online recipes

AU - Trattner, Christoph

AU - Moesslang, Dominik

AU - Elsweiler, David

PY - 2018/12/1

Y1 - 2018/12/1

N2 - Popularity prediction has been studied in diverse online contexts with demonstrable practical, sociological and technical benefit. Here, we add to the popularity prediction literature by studying the popularity of recipes on two large and well visited online recipe portals (Allrecipes.com, USA and Kochbar.de, Germany). Our analyses show differences between the platforms in terms of how the recipes are interacted with and categorized, as well as in the content of the food and its nutritional properties. For both datasets, we were able to show correlations between recipe features and proxies for popularity, which allow popularity of dishes to be predicted with some accuracy. The trends were more prominent in the Kochbar.de dataset, which was mirrored in the results of the prediction task experiments.

AB - Popularity prediction has been studied in diverse online contexts with demonstrable practical, sociological and technical benefit. Here, we add to the popularity prediction literature by studying the popularity of recipes on two large and well visited online recipe portals (Allrecipes.com, USA and Kochbar.de, Germany). Our analyses show differences between the platforms in terms of how the recipes are interacted with and categorized, as well as in the content of the food and its nutritional properties. For both datasets, we were able to show correlations between recipe features and proxies for popularity, which allow popularity of dishes to be predicted with some accuracy. The trends were more prominent in the Kochbar.de dataset, which was mirrored in the results of the prediction task experiments.

KW - Food

KW - Online recipes

KW - Popularity

UR - http://www.scopus.com/inward/record.url?scp=85049626449&partnerID=8YFLogxK

U2 - 10.1140/epjds/s13688-018-0149-5

DO - 10.1140/epjds/s13688-018-0149-5

M3 - Article

VL - 7

JO - EPJ Data Science

T2 - EPJ Data Science

JF - EPJ Data Science

SN - 2193-1127

IS - 1

M1 - 20

ER -