Skip to main content
SpringerLink
Log in

Addressing the complexity of personalized, context-aware and health-aware food recommendations: an ensemble topic modelling based approach

  • Published:
Journal of Intelligent Information Systems Aims and scope Submit manuscript

Abstract

Food Recommender Systems (FRS) have the potential to support informed and satisfying food choices. However, to realize their full potential, FRS must engage with the complexity of the choices people make around food. For example, while taste and ingredients are important, contextual and practical factors also play a critical role in food choice. Much of the previous literature on FRS has focused on ingredient-based recommendations, often in limited food datasets. Here we describe a broader approach, focusing on the use of Ensemble Topic Modelling (EnsTM) to support personalized recipe recommendations that implicitly capture and account for multi-domain food preferences in any food-corpus. EnsTM has the additional advantage of enabling a reduced data representation format that facilitates efficient user-modelling and recommendation. This article describes the results of two studies. The first investigated EnsTM based recommendation in a cold-start scenario. We investigated three different EnsTM based variations using a large-scale, real-world corpus of 230,876 recipes, and compared them with a conventional content-based approach. In a user study with 48 participants, EnsTM-based recommenders significantly outperformed the content-based approach. Alongside excellent coverage, they enabled an implicit understanding of users’ food preference across multiple food domains. The second study investigated the use of EnsTM in a long-term or regular-use scenario. We implemented multiple variations of feature and/or topic based hybrid recipe recommenders, which updated users’ profiles in real-time and predicted their preferences for new recipes. When compared against the current state of the art EnsTM-based recommenders performed significantly better, providing higher accuracy and coverage.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15

Similar content being viewed by others

References

  • Abdollahpouri, H., Burke, R., & Mobasher, B. (2019). Managing popularity bias in recommender systems with personalized re-ranking. 32nd Florida Artificial Intelligence Research Society Conference, FLAIRS. USA.

  • Ahn, J.w., Brusilovsky, P., Grady, J., He, D., & Syn, S.Y. (2007). Open user profiles for adaptive news systems: Help or harm?. In Proceedings of the 16th International conference on World Wide Web, WWW ’07 (pp. 11–20). New York: ACM.

  • Belford, M., Mac Namee, B., & Greene, D. (2018). Stability of topic modeling via matrix factorization. Expert Systems with Applications, 91(C), 159–169.

    Article  Google Scholar 

  • Belford, M., MacNamee, B., & Greene, D. (2016). Ensemble topic modeling via matrix factorization. In Artificial intelligence and cognitive science (AICS’16).

  • Blei, D.M., Ng, A.Y., & Jordan, M.I. (2003). Latent dirichlet allocation. Journal of Machine Learning Research, 3, 993–1022.

    MATH  Google Scholar 

  • Bobadilla, J., Ortega, F., Hernando, A., & Bernal, J. (2012). A collaborative filtering approach to mitigate the new user cold start problem. Knowledge-Based System, 26, 225–238.

    Article  Google Scholar 

  • Boutsidis, C., & Gallopoulos, E. (2008). Svd based initialization: a head start for nonnegative matrix factorization. Pattern Recognition, 41(4), 1350–1362.

    Article  Google Scholar 

  • Castro, J., Quesada, F.J., Palomares, I., & Martínez, L. (2015). A consensus-driven group recommender system. International Journal Intelligence Systems, 30(8), 887–906.

    Article  Google Scholar 

  • Cover, T., & Hart, P. (2006). Nearest neighbor pattern classification. IEEE Transactions Information Theory, 13(1), 21–27.

    Article  Google Scholar 

  • De Pessemier, T., Dooms, S., & Martens, L. (2013). A food recommender for patients in a care facility. In 7th ACM conference on recommender systems, RecSys ’13 (pp. 209–212).

  • Elsweiler, D., & Harvey, M. (2015). Towards automatic meal plan recommendations for balanced nutrition. In 9th ACM conference on recommender systems, RecSys ’15 (pp. 313–316).

  • Food dot com. (2021). https://www.food.com/. Accessed : March 2020.

  • Freyne, J., & Berkovsky, S. (2010). Intelligent food planning: Personalized recipe recommendation. In 15th International conference on intelligent user interfaces, IUI ’10 (pp. 321–324). USA.

  • Freyne, J., & Berkovsky, S. (2010). Recommending food: Reasoning on recipes and ingredients. In 18th, UMAP’10 (pp. 381–386): Springer-Verlag.

  • Freyne, J., Berkovsky, S., & Smith, G. (2011). Recipe recommendation: Accuracy and reasoning. In 19th, UMAP’11 (pp. 99–110): Springer-Verlag.

  • Ge, M., Elahi, M., Fernaández-Tobías, I., Ricci, F., & Massimo, D. (2015). Using tags and latent factors in a food recommender system. In 5th International conference on digital health 2015, DH ’15 (pp. 105–112). USA: ACM.

  • Ge, M., Ricci, F., & Massimo, D. (2015). Health-aware food recommender system. In 9th ACM conference on recommender systems, RecSys ’15 (pp. 333–334). USA: ACM.

  • Greene, D., O’Callaghan, D., & Cunningham, P. (2014). How many topics? stability analysis for topic models. In Machine learning and knowledge discovery in databases.

  • Gu, H., & Wang, D. (2009). A content-aware fridge based on rfid in smart home for home-healthcare. In 11th International conference on advanced communication technology, ICACT’09, (Vol. 2 pp. 987–990). Piscataway, NJ USA: IEEE Press.

  • Guo, L., Liang, J., Zhu, Y., Luo, Y., Sun, L., & Zheng, X. (2019). Collaborative filtering recommendation based on trust and emotion. Journal of Intelligent Information Systems, 53(1), 113–135.

    Article  Google Scholar 

  • Hall, M.A., & Smith, L.A. (1999). Feature selection for machine learning: Comparing a correlation-based filter approach to the wrapper. In Proceedings of the Twelfth International Florida Artificial Intelligence Research Society Conference (pp. 235–239): AAAI Press.

  • Harvey, M., Ludwig, B., & Elsweiler, D. (2013). You are what you eat: Learning user tastes for rating prediction. In 20th International symposium on string processing and information retrieval, SPIRE 2013, (Vol. 8214 pp. 153–164): Springer-Verlag.

  • Herlocker, J.L., Konstan, J.A., Terveen, L.G., & Riedl, J.T. (2004). Evaluating collaborative filtering recommender systems. ACM Transactions Information Systems, 22, 5–53.

    Article  Google Scholar 

  • Jawaheer, G., Weller, P., & Kostkova, P. (2014). Modeling user preferences in recommender systems: A classification framework for explicit and implicit user feedback. ACM Transactions Interaction Intelligence Systems, 4(2), 1–26.

    Article  Google Scholar 

  • Konjengbam, A., Kumar, N., & Singh, M. (2020). Unsupervised tag recommendation for popular and cold products. Journal of Intelligent Information Systems, 54.

  • Kuo, F.F., Li, C.T., Shan, M.K., & Lee, S.Y. (2012). Intelligent menu planning: Recommending set of recipes by ingredients. In ACM multimedia 2012 workshop on multimedia for cooking and eating activities, CEA ’12 (pp. 1–6). USA: ACM.

  • Konstan, J.A., & Riedl, J. (2012). Recommender systems: From algorithms to user experience. User Modeling and User-Adapted Interaction, 22, 101–123.

    Article  Google Scholar 

  • Landauer, T., Foltz, P., & Laham, D. (1998). An Introduction to Latent Semantic Analysis. Discourse Processes, 25, 259–284.

    Article  Google Scholar 

  • Lee, D.D., & Seung, H.S. (2000). Algorithms for non-negative matrix factorization. In 13th International conference on neural information processing systems, NIPS’00 (pp. 535–541). Cambridge: MIT Press.

  • Nguyen, T.T., Hui, P.M., Harper, F.M., Terveen, L., & Konstan, J.A. (2014). Exploring the filter bubble: the effect of using recommender systems on content diversity. In Proceedings of the 23rd international conference on World Wide Web (pp. 677–686).

  • Pazzani, M.J., & Billsus, D. (2007). The adaptive web. chap. Content-based recommendation Systems, (pp. 325–341). New York: Springer-Verlag.

    Google Scholar 

  • Potdar, K., Pardawala, T., & Pai, C. (2017). A comparative study of categorical variable encoding techniques for neural network classifiers. International Journal of Computer Applications, 175, 7–9.

    Article  Google Scholar 

  • Pu, W., Liu, N., Yan, S., Yan, J., Xie, K., & Chen, Z. (2007). Local word bag model for text categorization. In Seventh IEEE international conference on data mining (ICDM 2007) (pp. 625–630).

  • Ricci, F., Rokach, L., Shapira, B., Kantor, PB, & Shapira, B. (2015). Introduction to recommender systems. In Ricci, F., & Rokach, L. (Eds.) Recommender systems handbook, chap. 1 (pp. 1–29). Boston: Springer.

  • Ramos, J. (2003). Using tf-idf to determine word relevance in document queries. In Proceedings of the first instructional conference on machine learning (pp. 29–48).

  • Rokicki, M., Herder, E., Kuśmierczyk, T., & Trattner, C. (2016). Plate and prejudice: Gender differences in online cooking. In Proceedings of the 2016 conference on user modeling adaptation and personalization UMAP ’16 (pp. 207–215). USA: ACM.

  • Said, A., Kille, B., Jain, B.J., Albayrak, S., & Berlin, T.U. (2012). Increasing diversity through furthest neighbor-based recommendation. Proceedings of the 5th International Conference on Web Search and Data Mining, 12.

  • Sarwar, B., Karypis, G., Konstan, J., & Riedl, J. (2001). Item-based collaborative filtering recommendation algorithms. In Proceedings of the 10th international conference on World Wide Web (pp. 285–295).

  • Silveira, T., Zhang, M., Lin, X., Liu, Y., & Ma, S. (2019). How good your recommender system is? a survey on evaluations in recommendation. International Journal of Machine Learning and Cybernetics, 10.

  • Sobal, J.A., Bisogni, C., & Jastran, M. (2014). Food choice is multifaceted, contextual, dynamic, multilevel, integrated, and diverse. Journal of Mind, Brain, and Education, 8: Wiley.

  • Sobecki, J., Babiak, E., & Slanina, M. (2006). Application of hybrid recommendation in web-based cooking assistant. In 10th International conference on knowledge-based intelligent information and engineering systems - Volume Part III, KES’06 (pp. 797–804). Berlin: Springer.

  • Teng, C.Y., Lin, Y.R., & Adamic, L.A. (2012). Recipe recommendation using ingredient networks. In 4th Annual ACM Web science conference, WebSci ’12 (pp. 298–307). USA: ACM.

  • Topchy, A., Jain, A.K., & Punch, W.F. (2005). Clustering ensembles: models of consensus and weak partitions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(12), 1866–1881.

    Article  Google Scholar 

  • Tran, T.N.T., Atas, M., Felfernig, A., & Stettinger, M. (2018). An overview of recommender systems in the healthy food domain. Journal of Intelligent Information Systems, 50(3), 501–526.

    Article  Google Scholar 

  • Trattner, C., & Elsweiler, D. (2017). Food Recommender Systems: Important Contributions, Challenges and Future Research Directions. Computing Research Repository.

  • Trattner, C., & Elsweiler, D. (2017). Investigating the healthiness of internet-sourced recipes: Implications for meal planning and recommender systems. In 26th International conference on World Wide Web, WWW ’17 (pp. 489–498). Switzerland: IWWW-CSC.

  • Trattner, C., Moesslang, D., & Elsweiler, D. (2018). On the predictability of the popularity of online recipes. EPJ Data Science, 7(1), 20.

    Article  Google Scholar 

  • Trattner, C., Rokicki, M., & Herder, E. (2017). On the relations between cooking interests, hobbies and nutritional values of online recipes: Implications for health-aware recipe recommender systems. In Adjunct publication of the 25th conference on user modeling, adaptation and personalization, UMAP ’17 (pp. 59–64).

  • Ueda, M., Takahata, M., & Nakajima, S. (2011). User’s food preference extraction for personalized cooking recipe recommendation. In Second International Conference on Semantic Personalized Information Management: Retrieval and Recommendation, SPIM’11, Vol. 781.

  • Ueta, T., Iwakami, M., & Ito, T. (2011). A recipe recommendation system based on automatic nutrition information extraction. In 5th International conference on knowledge science, engineering and management, KSEM’11 (pp. 79–90). Berlin: Springer.

  • van Pinxteren, Y., Geleijnse, G., & Kamsteeg, P. (2011). Deriving a recipe similarity measure for recommending healthful meals. In 16th International conference on intelligent user interfaces, IUI ’11 (pp. 105–114). USA: ACM.

  • Wang, Q., Cao, Z., Xu, J., & Li, H. (2012). Group matrix factorization for scalable topic modeling. In Proceedings of the 35th International ACM SIGIR Conference on research and development in information retrieval, SIGIR ’12 (pp. 375–384).

  • Who fact sheet. (2018). http://www.who.int/mediacentre/factsheets/fs311/en/. Accessed : March 2018.

Download references

Funding

This research was supported by Science Foundation Ireland (SFI) under Grant Number 12/RC/2289_P2.

Author information

Authors and Affiliations

  1. Insight Centre for data analytics, University College Dublin, Dublin, Ireland

    Mansura A. Khan

  2. School of Computer Science, University College Dublin, Dublin, Ireland

    Barry Smyth & David Coyle

Authors
  1. Mansura A. Khan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Barry Smyth
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. David Coyle
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mansura A. Khan.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendix

Appendix

Table 5 Provides the proposed higher-level food feature and their corresponding Significance Scores.

Table 5 List of significant food features and their corresponding significance scores
Full size table

Table 6 provides the proposed Food topics and the corresponding features.

Table 6 Our proposed 30 food themes and their corresponding representative features
Full size table

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Khan, M.A., Smyth, B. & Coyle, D. Addressing the complexity of personalized, context-aware and health-aware food recommendations: an ensemble topic modelling based approach. J Intell Inf Syst 57, 229–269 (2021). https://doi.org/10.1007/s10844-021-00639-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10844-021-00639-8

Keywords

Search

Navigation