How users evaluate a recommender system goes beyond the accuracy of the presented content. For food recommendation, users difer in terms of the needs they have. We investigated whether users with diferent levels of health consciousness evaluated food recommender interfaces diferently, depending on two factors: the Preference Elicitation (PE) method and the use of a nutrition label 'boost', which is a nudge that is explained to the user. In an online study (2x2 between-subjects design; = 244 ), we compared a constraint-based recipe recommender, with feature-based PE, to a collaborative filtering recipe recommender with rating-based PE. Recipes were either annotated with a multiple trafic light nutrition label (i.e. the boost), or not (i.e., baseline). We found that boosts led to healthier recipe choices across both methods of PE. Moreover, we found users to be less satisfied with the constraint-based PE, while this may depend on the user's level of health consciousness.
Most recommender systems assume that people have both the capabilities and interest to make
fully-informed choices. That is, interaction data such as ratings and bookmarks are assumed
to be accurate reflections of one’s preferences [
In food recommender systems, which present personalized food or recipe content to users [
One overarching theme in food recommender systems is to support healthier choices [
In this paper, we examine recipe choices and a user’s evaluation for two recommender aspects
that go beyond algorithmic accuracy and the presented content. First, we investigate to what
extent ‘boosting’ can support healthier recipe choices in a food recommender context. Like
nudges [
Second, we investigate the role of the used preference elicitation method on a user’s evaluation
of a food recommender system. Whereas content-based and CF-based recommender typically
ask users to interact with individual items (cf. [
We argue that the extent to which users are interested in recipe healthiness can afect how they evaluate a recommender system and its preference elicitation method. On the one hand, in a collaborative filtering context, users can only indicate their interest in healthier recipes by rating specific recipes, while this might be easier in a recommender system that inquires on specific nutrition-related features, such as knowledge-based or constraint-based recommenders. On the other hand, users who aware of health and nutrition might be able to pick specific recipes that fit their needs and would experience feature-based elicitation as not fully meeting their needs. To this end, we consider a user’s level of health consciousness, which measures one’s perception of one’s diet and the relation between nutrient intake and health [29]. This aspect is adapted from pre-validated scales, used in nutritional studies [30, 29].
Approaches in food recommender systems promotes popular and unhealthy content, while user preferences tend to be more complex to be extracted. We propose the following research questions: • RQ1: To what extent does a ‘nutrition label boost’ steer users towards healthier recipe choices in a recommender system context? • RQ2: To what extent does a user’s evaluation of a food recommender system depend on the interplay between a user’s health consciousness and the system’s preference elicitation method?
We present an online recommender study in which users can disclose their preferences for recipes, after which they are presented a personalized recommendation list. By comparing recipe lists with and without nutrition labels and by using diferent preference elicitation methods, we show that: • Healthier recipe choices can be supported by boosts, without changing the recommended content. • A user’s perception (i.e., efort) and evaluation (i.e., choice dificulty and satisfaction) are more favorable among users of a constraint-based recommender with a low level of health consciousness, and vice versa for a collaborative filtering recommender.
We consulted a database that comprised recipes of Allrecipes.com, used in previous food
recommender systems studies (e.g., [
To address our research questions, and specifically RQ2, we compared two recommender
approaches that were distinct in terms of their preference elicitation (PE) methods1. Collaborative
Filtering (CF) relies on rating-based PE, asking users to indicate preferences for individual
items (i.e., recipes). Such approaches tend to outperform other item-based PE methods, such
as content-based recommendation [31]. In contrast, Constraint-based (CB) recommendation
exploits user preferences for recipe features, retrieving content based on the relation between
user characteristics and recipe features. Both of the selected approaches involve explicit
preference elicitation, as this was found to be the best representation of user preferences in food
domain [
Before implementing the CF-based recommender, we evaluated several rating-based prediction algorithms in an ofline setting using out dataset. The results of this analysis were also reported in [32]. Singular Value Decomposition (SVD) [33] was found to outperform algorithms (e.g., SVD++, KNNBasline, NMF ) by 10% in terms of the Root Mean Squared Error and Mean Absolute Error, and was deployed for our online evaluation.
As part of the study, users were presented 10 recipes to rate on a 5-point scale. These recipes were all part of a preferred cuisine by the user (cf. subsection 2.3). Subsequently, a list of ten recipes was retrieved that was closest to the inferred user profile, based on the SVD recommender. Five recipes were retrieved from a healthy set, and the other five were retrieved from a less healthy set ( cf. subsection 2.5.1 ).
Our CB recommender inquired on preferred user constraints for the recipe recommender. Rather
than relying on the relation between user characteristics and recipe features, such as was done in
the knowledge-based recommender of Musto et al. [
Users were subject to 2 (Preference Elicitation (PE): Collaborative Filtering (CF), ConstraintBased (CB)) X 2 (Labelling conditions: No label, Boost) between-subject design. For one arm, users either interacted with a CF-based or a CB system, which difered in terms of PE and the recommender algorithm. For the other arm, users either interacted with educational pages about the use of Multiple Trafic Light (MTL) nutrition labels, before being presented personalized 1Materials used for this study: https://github.com/ayoubGL/Boosting_TowardsHealth
What are your recipe preferences ? Please select the food category that like the most, then answer carefully the following questions. You will receive personalized recommendations according to your preferences.
Food category I want recipes at least with The preferred number of servings in my recipes are Preferred amount of calories in my recipes The time I have available for cooking (in min) The preferred number of ingredients in my recipes 3 stars 4 stars
No preferences min=1, max=10 min=200, max=1000 min=15, max=60 min=3, max=10
Next recipes annotated with MTL labels (i.e., Boost condition), or were not exposed to any education or label. Figure 2B depicts an example of an MTL label, Figure 3 depicts the educational prompt of the boost.
For the online evaluation, users were asked to provide their consent for participation. They were informed that our food recommender system would help them to find recipes they would like to cook and eat. Figure 2A depicts the user flow of the proposed system. First, users were asked to disclose basic demographic characteristics (e.g., age, gender, level of education) and to respond to questionnaire items about their level of health consciousness, as well as to choose a preferred food category. In the CF scenario, users were asked to rate ten recipes from the preferred category using a 5-star rating scale. In the CB scenario, the user filled out a form expressing her needs in terms of desired recipe features (see Figure 1). Users in both conditions were presented a list of ten personalized recipe recommendations, among which five were relatively healthy (i.e., having an FSA score of 8 or lower) and five relatively unhealthy (having an FSA score of 9 or higher). Recipes were either annotated with the Multiple Trafic Light (MTL) nutrition labels or not, according to the intervention conditions. Afterwards, users were asked to evaluate their perception of the system and their experience with the chosen recipes.
A total of 244 participants (75% female) completed our 5-minute study, for which they were rewarded with GBP 0.75. They were recruited on the crowdsourcing platform Prolific. They had at least an approval rate of 95% and previously completed at least 30 submissions. Among them, 99% had attained at least a high school diploma. Participants all lived in Great Britain, as Personal information & Health consciousness
Preferred food category
Recipe’s ratings Recipe features
Boost Boost
Personalized recipes
& No-label Personalized recipes
& MTL label Personalized recipes
& No-label Personalized recipes & MTL label
Choice & Evaluation Rating-based recommendations
Constraint-based recommendations
B Fiery Fish Tacos with Crunchy Corn Salsa
We assessed the healthiness of chosen recipes. In other studies, this was typically based on nutritional guidelines proposed by various health organizations [34, 35]. We used the wellvalidated FSA score [36], which was issued by the British Food Standards Agency [37]. The FSA score was computed by assigning points to four nutrients in a given recipe: sugar, fat, saturated fat, and salt. For each nutrient, we discerned between low, medium, or high content, assigning one point for each level (low, medium, high). This led to a scored scale from 4 (healthiest) to 12 (least healthy). We used a score of eight as a threshold to discern 50% healthy and 50% unhealthy recipes in our recommendation sets.
Understanding the use of nutrition labels On the next page, you will be presented personalized recipes recommendations, along with Multiple Traffic Light nutrition labels. Please carefully read the text bellow to understand what they mean before proceeding to the next page.
Nutritional labels give you information that can help you make healthier and more informed choices when deciding which food products to buy: “By checking the label each time you purchase something, you will take more control of your eating habits.” The traffic light labelling system will tell you whether a recipe has high, medium or low amount of fat, saturated fat, sugars and salt. It will also tell you how much of each nutrient a recipe contains per serving. • Red: means the product is high in a nutrient and you should try to cut down, eat less often or eat smaller amounts. • Amber: means medium, if a food contains mostly amber, you can eat it most of the time. • Green: means low, the more green lights a label shows, the healthier the food choice is.
Next
For our boosting intervention, we relied on a Front-of-Package Nutrition Label to inform users about the health content of recipes. For years, food products displayed nutritional details on the back of packaging. Although this was found to be associated with low-fat food intake and healthier food choices overall [38, 39], many people found the information too complex to use [40, 41]. This spurred the development of Front-of-Package labels that summarize a product’s nutritional content [42].
In this study, we used the Multiple Trafic Light (MTL) Front-of-Package nutrition label as a healthy eating boost (see Figure 2B). The MTL label was based on the FSA score, representing diferent levels of nutrient content by displaying red, amber, or green colors for high, medium, or low levels of nutrients, respectively [37].
To examine the user’s evaluation of our food recommender approaches, we inquired on user
characteristics and evaluation aspects. In line with the recommender system user experience
framework [43, 44], we examined perception and experience aspects and user characteristics.
Item responses were submitted to 5-point Likert Scales. Items for choice satisfaction [
Whether the items formed the expected aspects was examined using a principal component factor analysis. Table 2 outlines the results, describing the factor loadings for the used aspects and items. Items with low loadings or too many cross-loadings were removed from analysis. Whereas choice dificulty, choice satisfaction and perceived efort could be inferred reliably, there were doubts about the reliability of health consciousness. We observed a low value of Cronbach’s Alpha (0.37), even after dropping unreliable items. Since the used items were part of a pre-validated scale and the factor loadings with the retained items were good, we decided to proceed with our analyses including health consciousness.
For our analyses, all aspects were standardized and predicted using regression scoring. Health consciousness was considered as both a continuous and dichotomous variable. For the latter, we diferentiated between low and high levels of health consciousness, performing a mean split on the standardized variable.
I like the recipe I have chosen.
I think I will prepare the recipe I have chosen.
The chosen recipe fits my preference.
I know many recipes that I like more than the one I have chosen.
I would recommend the chosen recipe to others.
I changed my mind several times before making a decision.
Making a choice was overwhelming.
It was easy to make this choice.
My diet is well-balanced and healthy.
The amount of sugar I get in my food is important.
I have the impression that I sacrifice a lot for my health.
My health does not depend on the food I consume.
I am concerned about the quantity of salt that I get in my food.
The system takes up a lot of time.
I quickly understood the functionalities of the system.
Many actions were required to use the system.
Loading We present the analyses for our two research questions. First, we investigated to what extent annotating recipes with nutrition labels, with (i.e., boosting) or without (i.e., nudging) explanation, led to healthier recipe choices (RQ1). Second, we examined the interplay between the used Preference Elicitation (PE) method and user’s evaluation method, specifically examining how the user’s health consciousness and the PE method led to diferences in user perception (i.e., perceived efort) and evaluation (i.e., choice dificulty and choice satisfaction; RQ2).
We first examined to what extent nutrition label boosted afected the healthiness of recipes chosen. We performed a two-way ANCOVA to predict whether the FSA score of chosen recipes difered significantly across conditions, while adjusting for a user’s level of health consciousness. With regard to the labeling conditions, the results in Table 3 show that the FSA score was significantly lower in the boost condition ( = 7.98 , = 1.63 ) than in the no-label condition ( = 8.65 , = 1.50 ): (1, 239) = 10.41 , = 0.0014 . This showed that in the context of personalized recipe recommendations, boosting and annotating recipes with a multiple trafic light nutrition label leads to an increase in the healthiness of recipe choices.
The two-way ANCOVA reported in Table 3 further revealed that the healthiness of recipe choices did not depend on the Preference Elicitation (PE) method. Although chosen recipes were slightly less healthier after a constraint-based (CB) PE and recommendation method ( = 8.39 , = 1.39 ) than after a collaborative filtering (CF) PE ( = 8.23 , = 1.79 ), this diference was not significant ( = 0.42 ). This suggested that the used PE and recommendation method did not directly afect the recommended content.
In addition, we neither observed an interaction efect between the PE method and the use of a boosted nutrition label. To better understand all efects, please inspect Figure 4, which shows that users across both PE methods chose healthier recipes when being presented nutrition labels. Finally, Table 3 did not reveal that a user’s level of health consciousness significantly afected the healthiness of chosen recipes ( = 0.057 ); we further checked for interaction efects with the labelling conditions, but did not observe any.
Overall, we found that annotating recipes with multiple trafic light nutrition labels, in conjunction with an explanation, can support users in making healthier choices. On the other hand, the recommendation approach did not afect on the healthiness of chosen recipes (see Table 3), nor was it afected by a user’s level of health consciousness. Recipe choices were further related to how users evaluated our recommender system in the next subsection.
We examined a user’s evaluation of our recipe recommender system, based on the used Preference Elicitation (PE) method. In doing so, we first examined whether the user’s perception was afected by the interplay between a user’s health consciousness and the preference elicitation method (RQ2). Then, we examined whether this led to further diferences in a user’s experienced choice dificulty and choice satisfaction.
We performed a one-way ANCOVA on a user’s perceived efort of using our recommender system, including an interaction efect between health consciousness and the used PE method 2. The results are outlined in Table 4. We found no main efects for the used elicitation method, as the perceived efort of using the CB recommender ( = −.014 , = 1.03 ), which relied on disclosing preferences for recipe features, was only somewhat lower than that of the CF-based recommender ( = .014 , = .97 ), which relied on rating-based PE. In addition, we neither observed a main efect of a user’s health consciousness on efort: (1, 240) = 1.16 , = 0.28 .
What stands out from Table 4 is an interaction efect between the PE method and a user’s health: (1, 240) = 8.42 , = 0.0041 . This suggested that a user’s perceived efort depended on 2We also examined whether the user’s perceived efort difered across labelling conditions, such as by performing a two-way ANOVA across diferent labelling and PE conditions. However, we observed no diferences. the interplay between the PE method and the user’s level of health consciousness. The direction of this efect can be understood best by inspecting Figure 5, in which we diferentiated between low and high levels of health consciousness based on a mean split. While users with low levels of health consciousness perceived the CB method as less efortful, this increased significantly for users with a high level of health consciousness. In contrast, Figure 5 depicts much smaller diferences in perceived efort for a CF-based PE. This suggested that users who were likely to seek out healthier recipes found our constraint-based recommender, with feature-based elicitation, more efortful to use.
We further examined to what extent diferent elicitation methods and user characteristics afected the user experience aspects of choice dificulty and choice satisfaction. For each aspect, we performed a linear regression analysis, in which we also checked for diferences across labelling conditions, as well as whether perception aspects (i.e., efort) and choice metrics (i.e., FSA score) played a role.
Table 5 reports both analyses. For choice dificulty, we found that users of the constraintbased recommender found it more dificult to use ( = .31 , = 0.01 ), compared to users of our CF-based recommender. In contrast, choice dificulty was not afected by the use of nutrition labels (i.e., our boost), neither by the user’s level of health consciousness, nor by the interaction between the PE method and the user’s health consciousness (all > 0.05 ). This suggested that it was more dificult to choose between the recipes generated by the constraint-based recommender (compared to CF), while the use of labels did not support easier decision-making.
With regard to other aspects, we found that users who perceived a recommender as efortful to use, also reported higher levels of choice dificulty: = .26 , < 0.001 . This suggested a
Labelling Condition (Boost vs No label) Preference Elicitation (CB vs CF) Health Consciousness Preference Elicitation (CB vs CF) * Health Consciousness .0075 Choice Dificulty Perceived Efort FSA Intercept 2 .11 .31∗ .050 -.045 .37
S.E. .13 .12 .062 .13 .040 .33 .11∗∗∗ .26 ∗∗∗ .063 .13 .051 -.021 .033 .066 -.55 -.43∗∗ .12 -.21 ∗∗ .065
S.E. .13 .062 .13 .065 .040 .34 .11∗∗∗ possible indirect efect of the interplay between a user’s level of health consciousness and the PE method on choice dificulty, via perceived efort. Hence, an earlier analysis revealed that users in the CB condition reported higher levels of perceived efort if they had a higher level of health consciousness, and vice versa. In contrast, the healthiness of the chosen recipe (i.e., FSA) was not related to choice dificulty. Linear regression analyses, with models to predict the user’s experienced choice dificulty and choice satisfaction, based on the experimental conditions, user characteristics, perception aspects and choices. ‘Boost’ and ‘CB’ were coded as 0.5, ‘No label’ and ‘CF’ as -0.5. *** < 0.001, ** < 0.01, * < 0.05.
With regard to choice satisfaction, we observed similar efects as for choice dificulty. Again, we observed no significant efects for the use of nutritional labels, health consciousness and the chosen recipe’s FSA score. In a similar vein, users reported lower levels of choice satisfaction for our constraint-based recommender with feature-based PE ( = −.24 , = 1.02 ), than for our rating-based CF recommender ( = .24 , = .92 ): = −.43 , = 0.001 . In addition, we also observed a negative, significant relation between the experienced choice dificulty and choice satisfaction: = −.21 , = 0.002 . This suggested two possible mediated paths towards choice satisfaction. First, the constraint-based PE method increased the experienced choice dificulty and, in turn, lowered the user’s level of experienced choice satisfaction. Second, the interaction between a user’s health consciousness and the PE method afected efort, which afected choice dificulty and satisfaction subsequently. All the efects, regarding the experimental conditions, can be understood further by inspecting Figures 6 and 7.
We observed that the user’s evaluation of our food recommender system depended on the interplay between the PE method and user characteristics. Specifically, we observed that if a user’s level of health consciousness was high, users perceived higher levels of efort of using the constraint-based recommender, compared to lower levels of efort for users with a low level of health consciousness. Efort was further found to positively afect choice dificulty, which had, in turn, a negative relation with choice satisfaction. On top of that, users had on average more dificulties in choosing a recipe in the constraint-based condition, while we observed no efects on the used labeling condition. This showed that how a food recommender is evaluated depends on the healthy food interests of the user, which is one of the possible user characteristics that could have been inquired on.
In the context of personalized recipe recommendations, this work has examined two ways how
a recommender can cater to users who are interested in healthy eating. Food recommender
systems have faced dificulties in optimizing for nutritional content [
First, we have found that annotating recipes with nutrition labels leads to healthier recipe
choices (RQ1). Our work is among the first to examine such a digital nudge in a personalized
context [48], particularly in the domain food [49], and one of the first to use the concept of
‘boosting’ in a recommender system context. The idea that our (interface) interventions, not
only the algorithm, should be explainable to a person or user is gaining ground in behavioral
economics [
Second, we have found that the user’s evaluation of a food recommender system is significantly associated with the used preference elicitation method, based on that user’s level of health consciousness (RQ2). We have compared two distinct recommender approaches, collaborative ifltering and constraint-based, that also involve diferent methods of preference. Across all types of users, we find that constraint-based recipe recommendation lists are more dificult to choose from and, in turn, lead to lower levels of satisfaction. With regard to choice satisfaction, it could be argued that this outcome is unsurprising, since a constraint-based recommender system tends to be less efective than a CF-based recommender as it makes much simpler assumptions about the user’s preferences [51].
When combining health consciousness and the PE method, we would have expected to
observe an additional interaction efect. Hence, our user-specific analyses are more striking.
Similar to the interaction between knowledge and the PE method in [28], we have observed an
interaction efect between health consciousness and the PE method. However, although we have
observed lower perceived efort for lower levels of health consciousness and feature-based PE,
previous findings from the energy domain show the opposite with higher system satisfaction
levels for high domain knowledge and feature-based PE [
The main limitation to our findings it that health consciousness faced construct validity issues. Although the factor loadings of the eventually used items are good, the observed Cronbach’s Alpha was found to be too low and multiple items were dropped. This can raise some doubts about whether we have measured health consciousness reliably. Although we wholeheartedly recommended to replicate our findings, we have proceeded with our analysis in the current paper, because the used items are part of a pre-validated scale [30], implying that some studies have already used the scale without validating it further (e.g., [47]).
Another aspect that can be improved is the method of analysis. Whereas Knijnenburg et al.
[
A limitation regarding the recommended items is the arguably smaller dataset of recipes.
While some other studies with internet-sourced recipes have been able to leverage datasets
with more recipes [
Follow-up studies should also address the limitations of one-of user choices as a measure of recommender ‘success’. While food choices may go a long way in digital interfaces to predict subsequent user behavior (e.g., [56]), an optimal study design would also check whether chosen recipes are actually prepared and consumed. In a sense, repeated interactions with a recommender systems through some kind of application would be representative to assess whether user preferences would shift. Therefore, we opt for a recommender systems with a longitudinal design, as has been demonstrated in other domains [57].
This work was supported by industry partners and the Research Council of Norway with funding to MediaFutures: Research Centre for Responsible Media Technology and Innovation, through the centers for Research-based Innovation scheme, project number 309339.
New York: Cambridge 10 (2011) 1941904. [26] F. Ricci, L. Rokach, B. Shapira, Recommender systems: introduction and challenges, in:
Recommender systems handbook, Springer, 2015, pp. 1–34. [27] C. C. Aggarwal, Knowledge-based recommender systems, in: Recommender systems,
Springer, 2016, pp. 167–197. [28] B. P. Knijnenburg, M. C. Willemsen, Understanding the efect of adaptive preference elicitation methods on user satisfaction of a recommender system, in: Proceedings of the third ACM conference on Recommender systems, 2009, pp. 381–384. [29] S. J. Gould, Health consciousness and health behavior: the application of a new health consciousness scale, American Journal of Preventive Medicine 6 (1990) 228–237. [30] A. Gámbaro, A. C. Ellis, V. Prieto, Influence of subjective knowledge, objective knowledge and health consciousness on olive oil consumption—a case study, Food and Nutrition 4 (2013) 445–453. [31] C. Trattner, D. Elsweiler, An evaluation of recommendation algorithms for online recipe portals, in: Proceedings of the 4th International Workshop on Health Recommender Systems, CEUR, Aachen, DE, 2019. [32] A. El Majjodi, A. D. Starke, C. Trattner, Nudging towards health? examining the merits of nutrition labels and personalization in a recipe recommender system, in: Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization, 2022, pp. 48–56. [33] S. Funk, Netflix update: Try this at home (december 2006), 1999. URL: http://sifter.org/ simon/journal/20061211.html. [34] W. H. Organization, Diet, nutrition, and the prevention of chronic diseases: report of a joint WHO/FAO expert consultation, volume 916, World Health Organization, 2003. [35] H. Canada., The development and use of a surveillance tool: The classification of foods in the canadian nutrient file according to eating well with canada’s food guide, 2014. URL: http://publications.gc.ca/collections/collection_2014/sc-hc/H164-158-2-2014-eng.pdf. [36] A. D. Starke, M. C. Willemsen, C. Trattner, Nudging healthy choices in food search through visual attractiveness, Frontiers in Artificial Intelligence 4 (2021) 20. [37] Department of Health and Social Care UK, Front of Pack nutrition labelling guidance, 2016. URL: https://www.gov.uk/government/publications/ front-of-pack-nutrition-labelling-guidance. [38] K. Anastasiou, M. Miller, K. Dickinson, The relationship between food label use and dietary intake in adults: A systematic review, Appetite 138 (2019) 280–291. [39] M. L. Neuhouser, A. R. Kristal, R. E. Patterson, Use of food nutrition labels is associated with lower fat intake, Journal of the American dietetic Association 99 (1999) 45–53. [40] M. Cecchini, L. Warin, Impact of food labelling systems on food choices and eating behaviours: a systematic review and meta-analysis of randomized studies, Obesity reviews 17 (2016) 201–210. [41] K. G. Grunert, J. M. Wills, L. Fernández-Celemín, Nutrition knowledge, and use and understanding of nutrition information on food labels among consumers in the uk, Appetite 55 (2010) 177–189. [42] K. L. Hawley, C. A. Roberto, M. A. Bragg, P. J. Liu, M. B. Schwartz, K. D. Brownell, The science on front-of-package food labels, Public health nutrition 16 (2013) 430–439. [43] B. P. Knijnenburg, M. C. Willemsen, Z. Gantner, H. Soncu, C. Newell, Explaining the user experience of recommender systems, User modeling and user-adapted interaction 22 (2012) 441–504. [44] B. P. Knijnenburg, M. C. Willemsen, Evaluating recommender systems with user experiments, in: Recommender systems handbook, Springer, 2015, pp. 309–352. [45] A. D. Starke, C. Trattner, Promoting healthy food choices online: A case for multi-list recommender systems, in: Proceedings of the ACM IUI 2021 Workshops, CEUR, Aachen, DE, 2021. [46] M. C. Willemsen, M. P. Graus, B. P. Knijnenburg, Understanding the role of latent feature diversification on choice dificulty and satisfaction, User Modeling and User-Adapted Interaction 26 (2016) 347–389. [47] R. Mai, S. Hofmann, How to combat the unhealthy= tasty intuition: The influencing role of health consciousness, Journal of Public Policy & Marketing 34 (2015) 63–83. [48] M. Jesse, D. Jannach, Digital nudging with recommender systems: Survey and future directions, Computers in Human Behavior Reports 3 (2021) 100052. [49] M. Jesse, D. Jannach, B. Gula, Digital nudging for online food choices, Frontiers in
Psychology 12 (2021). [50] L. N. van der Laan, O. Orcholska, Efects of digital just-in-time nudges on healthy food choice–a field experiment, Food Quality and Preference 98 (2022). [51] A. Felfernig, R. Burke, Constraint-based recommender systems: technologies and research issues, in: Proceedings of the 10th international conference on Electronic commerce, 2008, pp. 1–10. [52] L. R. Flynn, R. E. Goldsmith, A short, reliable measure of subjective knowledge, Journal of business research 46 (1999) 57–66. [53] Z. Pieniak, J. Aertsens, W. Verbeke, Subjective and objective knowledge as determinants of organic vegetables consumption, Food quality and preference 21 (2010) 581–588. [54] R. M. Baron, D. A. Kenny, The moderator–mediator variable distinction in social psychological research: Conceptual, strategic, and statistical considerations., Journal of personality and social psychology 51 (1986) 1173. [55] A. Pardo, M. Román, Reflections on the baron and kenny model of statistical mediation,
Anales de psicologia 29 (2013) 614–623. [56] W.-Y. Chao, Z. Hass, Choice-based user interface design of a smart healthy food recommender system for nudging eating behavior of older adult patients with newly diagnosed type ii diabetes, in: International Conference on Human-Computer Interaction, Springer, 2020, pp. 221–234. [57] Y. Liang, M. C. Willemsen, A longitudinal study – exploring the efect of nudging on users’ genre exploration behavior and listening preference, in: Sixteenth ACM Conference on Recommender Systems, ACM, New York, NY, USA, 2022.