Increasing Diversity through Dynamic Critique in Conversational Recipe Recommendations

Conversational recommender systems help to guide users to discover items of interest while exploring the search space. During the exploration process, the user provides feedback on recommended items to refine subsequent recommendations. On one hand, critiquing as a way of feedback has proven effective for conversational interactions. On the other hand, diversifying the recommended items during exploration can help increase user understanding of the search space, which critiquing alone may not achieve. Both aspects are important elements for recommender applications in the food domain. Conversational exploration can help to introduce new food items, and diversity in diet has been shown to predict nutritional health. This paper introduces a novel approach that combines critique and diversity to support conversational recommendation in the recipe domain. Our initial evaluation in comparison to a baseline similarity-based recommender shows that the proposed approach increases diversity during the exploration process.

[1]  Gert B. M. Mensink,et al.  A new index to measure healthy food diversity better reflects a healthy diet than traditional measures. , 2007, The Journal of nutrition.

[2]  Shlomo Berkovsky,et al.  Intelligent food planning: personalized recipe recommendation , 2010, IUI '10.

[3]  Bart P. Knijnenburg,et al.  Recommender Systems for Self-Actualization , 2016, RecSys.

[4]  Eelco Herder,et al.  The Influence of City Size on Dietary Choices and Food Recommendation , 2017, UMAP.

[5]  Barry Smyth,et al.  Improving Recommendation Diversity , 2001 .

[6]  Albert-László Barabási,et al.  Flavor network and the principles of food pairing , 2011, Scientific reports.

[7]  Christoph Trattner,et al.  Plate and Prejudice: Gender Differences in Online Cooking , 2016, UMAP.

[8]  David C. Wilson,et al.  Personalised Specific Curiosity for Computational Design Systems , 2017 .

[9]  Sean M. McNee,et al.  Improving recommendation lists through topic diversification , 2005, WWW '05.

[10]  Christoph Trattner,et al.  How Editorial, Temporal and Social Biases Affect Online Food Popularity and Appreciation , 2017, ICWSM.

[11]  Saul Vargas,et al.  Coverage, redundancy and size-awareness in genre diversity for recommender systems , 2014, RecSys '14.

[12]  David Elsweiler,et al.  Automated Recommendation of Healthy, Personalised Meal Plans , 2015, RecSys.

[13]  Fiona S. L. Brinkman,et al.  FoodON: A Global Farm-to-Fork Food Ontology , 2016, ICBO/BioCreative.

[14]  Carl Anderson,et al.  A survey of food recommenders , 2018, ArXiv.

[15]  Bernd Ludwig,et al.  Bringing the "healthy" into Food Recommenders , 2015, DMRS.

[16]  Gianluca Stringhini,et al.  Kissing Cuisines: Exploring Worldwide Culinary Habits on the Web , 2016, WWW.

[17]  Barry Smyth,et al.  On the Role of Diversity in Conversational Recommender Systems , 2003, ICCBR.

[18]  Barry Smyth,et al.  On the Dynamic Generation of Compound Critiques in Conversational Recommender Systems , 2004, AH.

[19]  Kristian J. Hammond,et al.  Knowledge-Based Navigation of Complex Information Spaces , 1996, AAAI/IAAI, Vol. 1.

[20]  Mouzhi Ge,et al.  Using Tags and Latent Factors in a Food Recommender System , 2015, Digital Health.

[21]  Nadia Najjar,et al.  Critique Generation to Increase Diversity in Conversational Recipe Recommender System , 2021, FLAIRS Conference.

[22]  Barry Smyth,et al.  An Analysis of Critique Diversity in Case-Based Recommendation , 2005, FLAIRS.

[23]  Munmun De Choudhury,et al.  Characterizing Dietary Choices, Nutrition, and Language in Food Deserts via Social Media , 2016, CSCW.

[24]  Christoph Trattner,et al.  Temporal Patterns in Online Food Innovation , 2015, WWW.

[25]  Li Chen,et al.  Critiquing-based recommenders: survey and emerging trends , 2012, User Modeling and User-Adapted Interaction.

[26]  Shlomo Berkovsky,et al.  Recipe recommendation: accuracy and reasoning , 2011, UMAP'11.

[27]  Shuyang Li,et al.  Generating Personalized Recipes from Historical User Preferences , 2019, EMNLP.

[28]  Youri van Pinxteren,et al.  Deriving a recipe similarity measure for recommending healthful meals , 2011, IUI '11.

[29]  Michael Madary,et al.  Real Virtuality: A Code of Ethical Conduct. Recommendations for Good Scientific Practice and the Consumers of VR-Technology , 2016, Front. Robot. AI.

[30]  Jade Goldstein-Stewart,et al.  The use of MMR, diversity-based reranking for reordering documents and producing summaries , 1998, SIGIR '98.

[31]  Derek Bridge,et al.  Diversity, Serendipity, Novelty, and Coverage , 2016, ACM Trans. Interact. Intell. Syst..

[32]  Barry Smyth,et al.  Dynamic Critiquing , 2004, ECCBR.

[33]  Derek G. Bridge,et al.  Enhancing the diversity of conversational collaborative recommendations: a comparison , 2006, Artificial Intelligence Review.