Cataldo Musto, Alain D. Starke, Christoph Trattner, Amon Rapp, and Giovanni Semeraro. 2021. Exploring the Effects of Natural Language Justifications in Food Recommender Systems. In Proceedings of the 29th ACM
Conference on User Modeling, Adaptation and Personalization (UMAP ’21), June 21–25, 2021, Utrecht, Netherlands. ACM, New York, NY, USA, 11 pages. https://doi.org/10.1145/3450613.3456827
Climate change and variability and extreme events adaptation: what are the ch...ILRI
A presentation prepared by John Ingram for the workshop on Dealing with Drivers of Rapid Change in Africa: Integration of Lessons from Long-term Research on INRM, ILRI, Nairobi, June 12-13, 2008.
Catalysing the Sustainable and Inclusive Transformation of Food Systems, From...Francois Stepman
Presentation of Hélène David-Benz - Senior Researcher, French Agricultural Research Centre for International Development on 10 June 2021. Catalysing the Sustainable and Inclusive Transformation of Food Systems, From Assessment to Policy and Investment
Since 2020, the EU, FAO and CIRAD have entered into a partnership with governments and stakeholders to initiate a large-scale assessment and consultation on food systems in more than 50 countries.
Food systems transformation: what is the role of pulses in the sustainability...ExternalEvents
http://www.fao.org/globalsoilpartnership/en/
This presentation was presentaed during the seminar Soils & Pulses: symbiosis for life that took place at FAO HQ on 19 Apr 2016. it was made by Massimo Iannetta & Milena Stefanova and it presents the Food systems transformation.
Climate change and variability and extreme events adaptation: what are the ch...ILRI
A presentation prepared by John Ingram for the workshop on Dealing with Drivers of Rapid Change in Africa: Integration of Lessons from Long-term Research on INRM, ILRI, Nairobi, June 12-13, 2008.
Catalysing the Sustainable and Inclusive Transformation of Food Systems, From...Francois Stepman
Presentation of Hélène David-Benz - Senior Researcher, French Agricultural Research Centre for International Development on 10 June 2021. Catalysing the Sustainable and Inclusive Transformation of Food Systems, From Assessment to Policy and Investment
Since 2020, the EU, FAO and CIRAD have entered into a partnership with governments and stakeholders to initiate a large-scale assessment and consultation on food systems in more than 50 countries.
Food systems transformation: what is the role of pulses in the sustainability...ExternalEvents
http://www.fao.org/globalsoilpartnership/en/
This presentation was presentaed during the seminar Soils & Pulses: symbiosis for life that took place at FAO HQ on 19 Apr 2016. it was made by Massimo Iannetta & Milena Stefanova and it presents the Food systems transformation.
Sustainable intensification indicator framework for Africa RISINGafrica-rising
Presented by Philip Grabowski (Michigan State University), Mark Musumba (Columbia University), Cheryl Palm (University of Florida) and Sieg Snapp (Michigan State University) at the Africa RISING East and Southern Africa Phase II Planning Meeting, Lilongwe, Malawi, 5-8 October 2016
More meat, milk, and fish by and for the poor: CGIAR Research Program 3.7ILRI
Presented by Tom Randolph to the 2nd Multi-stakeholder Platform Meeting Agenda for Action for Sustainable Livestock Sector Development, Phuket, Thailand, 2 December 2011
Biotech Communications Workshop for Chinese Ministry of Agriculture and Triangle biotech professionals, Day 2
Presented by Zachary Brown, GES Center, NC State University
Tuesday, 10/3/2017
The 2nd evaluation focused on the analysis of the performance and effectiveness of responses to food and nutrition crises
Presentation by Ousman Tall, SWAC Secretariat, 3 December 2018.
Sustainable intensification indicator framework for Africa RISINGafrica-rising
Presented by Philip Grabowski (Michigan State University), Mark Musumba (Columbia University), Cheryl Palm (University of Florida) and Sieg Snapp (Michigan State University) at the Africa RISING East and Southern Africa Phase II Planning Meeting, Lilongwe, Malawi, 5-8 October 2016
More meat, milk, and fish by and for the poor: CGIAR Research Program 3.7ILRI
Presented by Tom Randolph to the 2nd Multi-stakeholder Platform Meeting Agenda for Action for Sustainable Livestock Sector Development, Phuket, Thailand, 2 December 2011
Biotech Communications Workshop for Chinese Ministry of Agriculture and Triangle biotech professionals, Day 2
Presented by Zachary Brown, GES Center, NC State University
Tuesday, 10/3/2017
The 2nd evaluation focused on the analysis of the performance and effectiveness of responses to food and nutrition crises
Presentation by Ousman Tall, SWAC Secretariat, 3 December 2018.
Intelligenza Artificiale e Social Media - Monitoraggio della Farnesina e La M...Cataldo Musto
Convegno a Porte Chiuse dell'Associazione Italiana per l'Intelligenza Artificiale insieme al Ministero per gli Affari Esteri e la Cooperazione Internazionale - 30 Giugno 2021
Natural Language Justifications for Recommender Systems Exploiting Text Summa...Cataldo Musto
Natural Language Justifications for Recommender Systems Exploiting Text Summarization and Sentiment Analysis - AI*IA 2019 - Italian Conference on Artificial Intelligence
A Framework for Holistic User Modeling Merging Heterogeneous Digital FootprintsCataldo Musto
A Framework for Holistic User Modeling Merging Heterogeneous Digital Footprints - HUM 2018 – Holistic User Modeling Workshop jointly held with
UMAP 2018 – 26th International
Conference on User Modeling,
Adaptation and Personalization
Singapore - July 8, 2018
UiPath Test Automation using UiPath Test Suite series, part 3DianaGray10
Welcome to UiPath Test Automation using UiPath Test Suite series part 3. In this session, we will cover desktop automation along with UI automation.
Topics covered:
UI automation Introduction,
UI automation Sample
Desktop automation flow
Pradeep Chinnala, Senior Consultant Automation Developer @WonderBotz and UiPath MVP
Deepak Rai, Automation Practice Lead, Boundaryless Group and UiPath MVP
Essentials of Automations: Optimizing FME Workflows with ParametersSafe Software
Are you looking to streamline your workflows and boost your projects’ efficiency? Do you find yourself searching for ways to add flexibility and control over your FME workflows? If so, you’re in the right place.
Join us for an insightful dive into the world of FME parameters, a critical element in optimizing workflow efficiency. This webinar marks the beginning of our three-part “Essentials of Automation” series. This first webinar is designed to equip you with the knowledge and skills to utilize parameters effectively: enhancing the flexibility, maintainability, and user control of your FME projects.
Here’s what you’ll gain:
- Essentials of FME Parameters: Understand the pivotal role of parameters, including Reader/Writer, Transformer, User, and FME Flow categories. Discover how they are the key to unlocking automation and optimization within your workflows.
- Practical Applications in FME Form: Delve into key user parameter types including choice, connections, and file URLs. Allow users to control how a workflow runs, making your workflows more reusable. Learn to import values and deliver the best user experience for your workflows while enhancing accuracy.
- Optimization Strategies in FME Flow: Explore the creation and strategic deployment of parameters in FME Flow, including the use of deployment and geometry parameters, to maximize workflow efficiency.
- Pro Tips for Success: Gain insights on parameterizing connections and leveraging new features like Conditional Visibility for clarity and simplicity.
We’ll wrap up with a glimpse into future webinars, followed by a Q&A session to address your specific questions surrounding this topic.
Don’t miss this opportunity to elevate your FME expertise and drive your projects to new heights of efficiency.
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Albert Hoitingh
In this session I delve into the encryption technology used in Microsoft 365 and Microsoft Purview. Including the concepts of Customer Key and Double Key Encryption.
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...DanBrown980551
Do you want to learn how to model and simulate an electrical network from scratch in under an hour?
Then welcome to this PowSyBl workshop, hosted by Rte, the French Transmission System Operator (TSO)!
During the webinar, you will discover the PowSyBl ecosystem as well as handle and study an electrical network through an interactive Python notebook.
PowSyBl is an open source project hosted by LF Energy, which offers a comprehensive set of features for electrical grid modelling and simulation. Among other advanced features, PowSyBl provides:
- A fully editable and extendable library for grid component modelling;
- Visualization tools to display your network;
- Grid simulation tools, such as power flows, security analyses (with or without remedial actions) and sensitivity analyses;
The framework is mostly written in Java, with a Python binding so that Python developers can access PowSyBl functionalities as well.
What you will learn during the webinar:
- For beginners: discover PowSyBl's functionalities through a quick general presentation and the notebook, without needing any expert coding skills;
- For advanced developers: master the skills to efficiently apply PowSyBl functionalities to your real-world scenarios.
DevOps and Testing slides at DASA ConnectKari Kakkonen
My and Rik Marselis slides at 30.5.2024 DASA Connect conference. We discuss about what is testing, then what is agile testing and finally what is Testing in DevOps. Finally we had lovely workshop with the participants trying to find out different ways to think about quality and testing in different parts of the DevOps infinity loop.
The Art of the Pitch: WordPress Relationships and SalesLaura Byrne
Clients don’t know what they don’t know. What web solutions are right for them? How does WordPress come into the picture? How do you make sure you understand scope and timeline? What do you do if sometime changes?
All these questions and more will be explored as we talk about matching clients’ needs with what your agency offers without pulling teeth or pulling your hair out. Practical tips, and strategies for successful relationship building that leads to closing the deal.
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf91mobiles
91mobiles recently conducted a Smart TV Buyer Insights Survey in which we asked over 3,000 respondents about the TV they own, aspects they look at on a new TV, and their TV buying preferences.
Securing your Kubernetes cluster_ a step-by-step guide to success !KatiaHIMEUR1
Today, after several years of existence, an extremely active community and an ultra-dynamic ecosystem, Kubernetes has established itself as the de facto standard in container orchestration. Thanks to a wide range of managed services, it has never been so easy to set up a ready-to-use Kubernetes cluster.
However, this ease of use means that the subject of security in Kubernetes is often left for later, or even neglected. This exposes companies to significant risks.
In this talk, I'll show you step-by-step how to secure your Kubernetes cluster for greater peace of mind and reliability.
Welocme to ViralQR, your best QR code generator.ViralQR
Welcome to ViralQR, your best QR code generator available on the market!
At ViralQR, we design static and dynamic QR codes. Our mission is to make business operations easier and customer engagement more powerful through the use of QR technology. Be it a small-scale business or a huge enterprise, our easy-to-use platform provides multiple choices that can be tailored according to your company's branding and marketing strategies.
Our Vision
We are here to make the process of creating QR codes easy and smooth, thus enhancing customer interaction and making business more fluid. We very strongly believe in the ability of QR codes to change the world for businesses in their interaction with customers and are set on making that technology accessible and usable far and wide.
Our Achievements
Ever since its inception, we have successfully served many clients by offering QR codes in their marketing, service delivery, and collection of feedback across various industries. Our platform has been recognized for its ease of use and amazing features, which helped a business to make QR codes.
Our Services
At ViralQR, here is a comprehensive suite of services that caters to your very needs:
Static QR Codes: Create free static QR codes. These QR codes are able to store significant information such as URLs, vCards, plain text, emails and SMS, Wi-Fi credentials, and Bitcoin addresses.
Dynamic QR codes: These also have all the advanced features but are subscription-based. They can directly link to PDF files, images, micro-landing pages, social accounts, review forms, business pages, and applications. In addition, they can be branded with CTAs, frames, patterns, colors, and logos to enhance your branding.
Pricing and Packages
Additionally, there is a 14-day free offer to ViralQR, which is an exceptional opportunity for new users to take a feel of this platform. One can easily subscribe from there and experience the full dynamic of using QR codes. The subscription plans are not only meant for business; they are priced very flexibly so that literally every business could afford to benefit from our service.
Why choose us?
ViralQR will provide services for marketing, advertising, catering, retail, and the like. The QR codes can be posted on fliers, packaging, merchandise, and banners, as well as to substitute for cash and cards in a restaurant or coffee shop. With QR codes integrated into your business, improve customer engagement and streamline operations.
Comprehensive Analytics
Subscribers of ViralQR receive detailed analytics and tracking tools in light of having a view of the core values of QR code performance. Our analytics dashboard shows aggregate views and unique views, as well as detailed information about each impression, including time, device, browser, and estimated location by city and country.
So, thank you for choosing ViralQR; we have an offer of nothing but the best in terms of QR code services to meet business diversity!
Exploring the Effects of Natural Language Justifications in Food Recommender Systems
1. CATALDO MUSTO*, ALAIN STARKE#,^, CHRISTOPH TRATTNER^, AMON RAPP°, GIOVANNI SEMERARO*
(*) UNIVERSITÀ DEGLI STUDI DI BARI ‘ALDO MORO’ – ITALY (#) WAGENINGEN UNIVERSITY & RESEARCH – THE NETHERLANDS
(^) UNIVERSITY OF BERGEN – NORWAY (°) UNIVERSITY OF TORINO - ITALY
Exploring the Effects of
Natural Language Justifications
in Food Recommender Systems
ACM UMAP 2021 – 29th Int. Conf. on User Modeling, Adaptation and Personalization - Online from Utrecht - June 23, 2021
2. Background
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
3. Health-aware Food RecSys
?
Goal: to identify - among a set of suitable suggestions -
the healthiest recipes for a target user
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
4. Health-aware Food RecSys
Goal: to identify - among a set of suitable suggestions -
the healthiest recipes for a target user
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
5. Health-aware Food RecSys
!
Problem: users tend to prefer
popular (and unhealthy) recipes (^) (*)
(^) Christoph Trattner and David Elsweiler. 2017. Investigating the
healthiness of internet-sourced recipes: implications for meal planning
and recommender systems. In Proceedings of the 26th international
conference on world wide web. 489–498.
(*) Cataldo Musto , Christoph Trattner, Alain Starke, Giovanni Semeraro:
Towards a Knowledge-aware Food Recommender System
Exploiting Holistic User Models. UMAP 2020: 333-337
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
6. How can we encourage
people to make
healthier food choices?
RESEARCH PROBLEM
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
7. Contribution
▪We design a NLP pipeline that automatically
generates Natural Language Justifications
▪Instead of just showing a recommendation, we also
generate a justification supporting the suggestion
▪ Our conjecture
▪More informed users make healthier food
choices
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
8. Use Case
«Vegetable Soup has less calories and more proteins than spaghetti cacio and
pepper. Moreover, spaghetti cacio and pepper has more satured fats.
To intake many saturated fats increases the risk of heart diseases.
Given your high BMI, you should consider this.»
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
9. Methodology
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
10. Our Workflow
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
11. Step 1: PROFILER
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
12. Step 1: PROFILER
Demographics
Affect
Behavioral Data
Health Data
Domain Knowledge
Preferences and Goals
Mood (positive, negative, neutral)
Level of Physical Activity
Cooking Experience, Available Time,
Cost Constraints
Lifestyle, Amount of Sleep, Stress Level, BMI
Gender, Age, Weight, Height
Food Preferences and Restrictions
Personal Goals (e.g., Losing Weight)
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
13. Step 2: RECIPE ANALYZER
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
14. Step 2: RECIPE ANALYZER
++ +++
++
+ ++
Input
Output
One or two recipes
Information about the recipes (amount of macro-nutrients or a comparison)
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
15. Step 3: GENERATOR
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
16. Step 3: FOOD KNOWLEDGE BASE
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
17. Step 3: FOOD KNOWLEDGE BASE
Encodes common-sense and general knowledge about food consumption, risks and benefits
For each macro-nutrient, around 10 facts are encoded in the knowledge base. 150 in total.
HIGH HIGH
STROKE
RISK
SATURATED
FATS
HIGH HIGH
PRESSURE
RISK
SODIUM
HIGH HIGH
MUSCLE
DEVELOPMENT
PROTEINS
HIGH
SUGAR
IMPROVES
MOOD
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
18. Workflow Recap
vs.
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
19. How are the
justifications generated?
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
20. Justification Styles and Strategies
▪Based on the principles of Natural Language Generation
▪All the justifications are dynamically built by our workflow
▪Template-based structure, filled in based on user’s features and recipes
characteristics
Two different justification styles
Single Explains the features of each recipe separately
Comparative Provides a comparison of the two recipes
Eight justification strategies
Each justification strategy highlights and emphasizes a different aspect of the
recommended recipe (e.g., nutrients, popularity, healthiness, health risks and
benefits, etc.)
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
21. Justification Styles and Strategies
▪Based on the principles of Natural Language Generation
▪ All the justifications are dynamically built by our workflow
▪ Template-based structure, filled in based on user’s features and recipes characteristics
▪Two different justification styles
▪ Single Explains the features of each recipe separately
▪ Comparative Provides a comparison of the two recipes
Eight justification strategies
Each justification strategy highlights and emphasizes a different aspect of the
recommended recipe (e.g., nutrients, popularity, healthiness, health risks and benefits,
etc.)
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
22. Justification Styles and Strategies
▪Based on the principles of Natural Language Generation
▪ All the justifications are dynamically built by our workflow
▪ Template-based structure, filled in based on user’s features and recipes characteristics
▪Two different justification styles
▪ Single Explains the features of each recipe separately
▪ Comparative Provides a comparison of the two recipes
▪ Eight justification strategies
▪ Each justification strategy highlights and emphasizes a different aspect of the
recommended recipe (e.g., nutrients, popularity, healthiness, health risks and benefits,
etc.)
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
23. Overview of the Strategies:
Description and Popularity
▪ ‘Baseline’ justification strategies
▪ Description Provides a textual description of the recipe
▪ Popularity Shows how popular is the recipe
Spaghetti Cacio and Pepper are one
of the dishes of the Roman Tradition:
grated pecorino and peppercorns,
a quick and tasty recipe.
Vegetable Soup is a genuine and
healthy dish, a perfect winter
comfort food
Spaghetti cacio and pepper is more
popular than Vegetable Soup
in the community
vs.
DESCRIPTION – SINGLE STYLE POPULARITY – COMPARATIVE STYLE
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
24. Overview of the Strategies:
User’s Skills, User Goals, User Lifestyle
▪ Link user’s information to the characteristics of the recipe
▪ User Features: User’s cooking skills, self-set goals, personal lifestyle
▪ Recipe Features: difficulty, calories and healthiness of the recipe
vs.
USER SKILLS – SINGLE STYLE
Spaghetti cacio and pepper
has more calories than
Vegetable Soup (491 vs.
462). Vegetable soup can
better help to reach your goal
of losing weight.
z
Spaghetti Cacio and Paper has a medium
level of difficulty. It might not be adequate to
your cooking skills, which are low.
Vegetable Soup is very easy to prepare. The
recipe seems adequate to your cooking
skills, which are low.
USER GOALS – COMPARATIVE STYLE
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
25. Overview of the Strategies
Food Features, Health Risks and Benefits
▪Highlight distinctive characteristics of the recipes and links information
about macro-nutrients to health risks (or benefits, respectively)
▪Input Features: macro-nutrients, user characteristics (BMI, mood, sleep, stress, etc.), facts
from food knowledge
vs.
Spaghetti Cacio and Pepper has a higher amount of saturated fats
(8.7gr vs. 4.55gr) and a lower amount of fibers (4.55gr vs. 7.3gr)
than Vegetable Soup.
To intake many saturated fats increases the risk of heart diseases.
Given your high BMI, you should take into account this fact. On the
other side, to intake many fibers increases the risk of constipation.
HEALTH RISKS – COMPARATIVE STYLE
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
27. Method
• 4,671 Mediterranean-style recipes
• 503 participants (Amazon MTurk) completed the study:
1. Disclosed personal information
2. Chose 3 x 1 recipe from a pair (healthy vs popular): a first course, second course, and a dessert
• Recipe pairs were subject to 3 between-user conditions, presented with either:
◦ No Justifications (baseline)
◦ Single-style Justifications
◦ Comparative-style Justifications
• For each pair, we randomly used one of the eight justification strategies.
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
28. Interface
Justification
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
Choice
Motivation
29. Results
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
30. Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
Recipe Choices Across Conditions
and Meal Types
→ % of Healthy Choices was higher for comparative justifications, compared to the ‘no
justification baseline’.
→ No such effects for single justifications
31. Effectiveness of Specific Strategies
Across all meal types:
◦ No strategy decreased the likelihood of choosing a healthy recipe
◦ Food Features and Health Risks Strategies increased the likelihood
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
32. Why Did Users Choose Healthy Recipes?
Analysis of Choice Motivation
Logistic regression analyses, predicting healthy recipe choices using all choice motivations
Clearest effects across all meal types:
◦ Taste was negatively related to reasons for choosing a healthy recipe
◦ Health was positively related to choosing healthy recipes
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
33. Concluding Remarks
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
34. Conclusions and Future Work
•Our NLP pipeline captures: Eating preferences (User) and features (Recipes), to generate
healthy recipe advice, with justifications.
• Comparative Justifications can support user goals, on top of personalized recommendations
• Our healthy Recs are founded in a user’s choice motivation
• Future work: Can recommender support changes in eating habits, by combining *what*
should be recommended with *how*?
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021
35. Questions are welcome!
cataldo.musto@uniba.it, alain.starke@wur.nl
@cataldomusto, @alainstarke
Contacts
Cataldo Musto, Alain Starke, Christoph Trattner, Amon Rapp, Giovanni Semeraro
Exploring the Effects of Natural Language Justifications in Food Recommender Systems. UMAP 2021 – Online – June 23, 2021