A recipe based on-line food store
Martin Svensson2000, Proceedings of the 5th international conference on Intelligent user interfaces
Sign up for access to the world's latest research
checkGet notified about relevant papers
checkSave papers to use in your research
checkJoin the discussion with peers
checkTrack your impact
Abstract
Recent research in the area of information retrieval hypothesizes that people benefit from social clues, so called social navigation, when they try to navigate information spaces [7]. We have designed an on-line grocery store building upon those ideas manifested in several different ways. The most central feature is that the system uses a combination of content-based and collaborative filtering as the basis for recipe recommendations. This filtering process can in turn be controlled by editors, whose role is to control the content of the "recipe clubs". Other types of social clues are also present, such as displaying how many users that have chosen a recipe. Finally, the system shows information about other users currently present in the system, and allows users to get in direct contact through chat.
Related papers
Social navigation of food recipes
2001
The term Social Navigation captures every-day behaviour used to find information, people, and places -namely through watching, following, and talking to people. We discuss how to design information spaces to allow for social navigation. We applied our ideas in a recipe recommendation system. In a follow-up user study, subjects state that social navigation adds value to the service: it provides for social affordance, and it helps turning a space into a social place. The study also reveals some unresolved design issues, such as the snowball effect where more and more users follow each other down the wrong path, and privacy issues.
Designing and evaluating kalas: A social navigation system for food recipes
ACM Transactions on Computer-human Interaction, 2005
The idea of social navigation is to aid users to navigate information spaces through making the collective, aggregated, or individual actions of others visible and useful as a basis for making decisions on where to go next and what to choose. These social markers should also help in turning the navigation experience into a social and pleasurable one rather than the tedious, boring, frustrating and sometimes even scary experience of a lonely traveler. To evaluate whether it is possible to design for social navigation, we built the food recipe system Kalas. It includes several different forms of aggregated trails of user actions and means of communication between users: recommender system functionality (recommendations computed from others' choices), real-time broadcasting of concurrent user activity in the interface, possibilities to comment and vote on recipes, the number of downloads per recipe, and chatting facilities. Recipe author was also included in the recipe description. Kalas was tried with 302 users during six months, where 73 of the users answered a final questionnaire. The overall impression was that users liked and acted on aggregated trails and navigated differently because of them. 18% of the selected recipes came from the list of recommended recipes. About half of the 73 users understood that recommendations were computed from their own and others actions, while the rest had not reflected upon it or had erroneous beliefs. Interestingly both groups selected a large proportion of their recipes from the recommendations. Unfortunately, there were not enough users to populate the space at every occasion, and thus both chatting and following other users moving in the space was for the most part not possible, but when possible, users move to the space where most other users could be found. Of the other social textures, users themselves claimed to be most influenced by other users' comments attached to the recipes, and less by recipe author or number of downloads. Users are more positive to the possibility of expressing themselves in terms of comments and voting, than to seeing the comments and votes by others. It was noted that users did not pick more recommended recipes towards the end of the study period when the accuracy of recommendations should have been higher. More or less from the start, they picked recommended recipes and went on doing so throughout the whole period.
Design implications for a community-based social recipe system
World Congress on Sustainable Technologies (WCST-2014), 2014
We introduced the concept of a community-based social recipe system which suggests recipes to groups of users based on available ingredients from these users (i.e. who can be from the same household or different households). In this paper we discuss the relevance and desirability of such a system and how it should be designed based on user studies. We identified the relevance of targeting ingredients and found positive expected experiences with the system such as to prevent habitual waste-related behavior, awareness of in-home food availability, creativity in cooking, moments for surprises and spontaneity, coordination among a group of friends, education and connectedness. Possible reasons of not using the system are trust and the inconvenience of distance among users in a group that are suggested with a social recipe. From our findings, we specify design implications for the system and optimization functions aiming at the prevention of food waste at a collective level.
Recommendation, collaboration and social search
2011
This chapter considers the social component of interactive information retrieval: what is the role of other people in searching and browsing? For simplicity we begin by considering situations without computers. After all, you can interactively retrieve information without a computer; you just have to interact with someone or something else.
Exploring Folksonomy and Cooking Procedures to Boost Cooking Recipe Recommendation
2011
Recommender systems have gained great popularity in Internet applications in recent years, due to that they facilitate users greatly in information retrieval despite the explosive data growth. Similar to other popular domains such as the movie-, music-, and book- recommendations, cooking recipe selection is also a daily activity in which user experiences can be greatly improved by adopting appropriate recommendation strategies. Based on content-based and collaborative filtering approaches, we present in this paper a comprehensive recipe recommendation framework encompassing the modeling of the recipe cooking procedures and adoption of folksonomy to boost the recommendations. Empirical studies are conducted on a real data set to show that our method outperforms baselines in the recipe domain.
An overview of recommender systems in the healthy food domain
Journal of Intelligent Information Systems, 2017
Recently, food recommender systems have received increasing attention due to their relevance for healthy living. Most existing studies on the food domain focus on recommendations that suggest proper food items for individual users on the basis of considering their preferences or health problems. These systems also provide functionalities to keep track of nutritional consumption as well as to persuade users to change their eating behavior in positive ways. Also, group recommendation functionalities are very useful in the food domain, especially when a group of users wants to have a dinner together at home or have a birthday party in a restaurant. Such scenarios create many challenges for food recommender systems since the preferences of all group members have to be taken into account in an adequate fashion. In this paper, we present an overview of recommendation techniques for individuals and groups in the healthy food domain. In addition, we analyze the existing state-of-the-art in food recommender systems and discuss research challenges related to the development of future food recommendation technologies.
A Recommender System for Healthy and Personalized Recipes Recommendations
2020
Unhealthy eating behavior is a serious public health issue with massive repercussions on an individual’s health. One potential solution to this problem is to help people change their eating behavior by developing systems able to recommend healthy recipes that can influence eating behavior. One challenge for such systems is to deliver healthy recommendations that take into account users’ needs and preferences, while also informing users about the healthiness of the recommended recipes. In this paper, we investigate whether introducing a healthy bias in a recipe recommendation algorithm, and displaying a healthy tag on recipe cards would have an influence on people’s decision making. To that end, we build three different recipes recommender systems: one that recommends recipes matching users’ preferences, another one that only recommends healthy recipes, and a third one that recommends recipes that are both healthy and match users’ preferences. We evaluate these three systems through ...
Personalized search-integrating collaboration and social networks
2010
Despite improvements in their capabilities, search engines still fail to provide users with only relevant results. One reason is that most search engines implement a “one size fits all” approach that ignores personal preferences when retrieving the results of a user's query. Recent studies (Smyth, 2010) have elaborated the importance of personalizing search results and have proposed integrating recommender system methods for enhancing results using contextual and extrinsic information that might indicate the user's actual needs. In this article, we review recommender system methods used for personalizing and improving search results and examine the effect of two such methods that are merged for this purpose. One method is based on collaborative users' knowledge; the second integrates information from the user's social network. We propose new methods for collaborative‐and social‐based search and demonstrate that each of these methods, when separately applied, produce more accurate search results than does a purely keyword‐based search engine (referred to as “standard search engine”), where the social search engine is more accurate than is the collaborative one. However, separately applied, these methods do not produce a sufficient number of results (low coverage). Nevertheless, merging these methods with those implemented by standard search engines overcomes the low‐coverage problem and produces personalized results for users that display significantly more accurate results while also providing sufficient coverage than do standard search engines. The improvement, however, is significant only for topics for which the diversity of terms used for queries among users is low. © 2011 Wiley Periodicals, Inc.
A Hybrid Restaurant Recommender General Terms Hybrid Restaurant Recommender System, Data mining
In any e-commerce application, the recommender systems play a vital role as they assist the prospective buyers in making proper decisions on the basis of the recommendations that the system provides. Recommender systems aim at providing the users with effective recommendations based on their intuitions and preferences. The two very old techniques commonly used for providing automated recommendations are collaborative filtering and knowledge based filtering techniques. However, both these techniques have certain drawbacks when used separately. In this paper, we propose architecture for designing hybrid recommender system that combines the advantages of both the techniques; thereby improving accuracy. The proposed approach uses a combination of personalised recommendations (based on individuals past behaviour), social recommendations (based on past behaviour of similar users) and item-based recommendations (based on restaurant database). This combination overcomes all the drawbacks that are faced when these techniques are used separately. In this paper, we have described the application of such a system within the domain of restaurants. Keywords Hybrid recommender system, restaurant recommender system, collaborative filtering and knowledge based recommender system, web log records
Collaborative and Social Information Retrieval and Access
2009
Traditionally information retrieval (IR) research has focussed on a single user interaction modality, where a user searches to satisfy an information need. Recent advances in both Web technologies, such as the sociable Web of Web 2.0, and computer hardware, such as tabletop interface devices, have enabled multiple users to collaborate on many computer-related tasks. Due to these advances there is an increasing need to support two or more users searching together at the same time, in order to satisfy a shared information need, which we refer to as Synchronous Collaborative Information Retrieval. Synchronous Collaborative Information Retrieval (SCIR) represents a significant paradigmatic shift from traditional IR systems. In order to support an effective SCIR search, new techniques are required to coordinate users' activities. In this chapter we explore the effectiveness of a sharing of knowledge policy on a collaborating group. Sharing of knowledge refers to the process of passing relevance information across users, if one user finds items of relevance to the search task then the group should benefit in the form of improved ranked lists returned to each searcher.In order to evaluate the proposed techniques the
Related topics
Cited by
A Content-Based Matrix Factorization Model for Recipe Recommendation
Lecture Notes in Computer Science, 2014
An overview of recommender systems in the healthy food domain
Journal of Intelligent Information Systems, 2017
Recently, food recommender systems have received increasing attention due to their relevance for healthy living. Most existing studies on the food domain focus on recommendations that suggest proper food items for individual users on the basis of considering their preferences or health problems. These systems also provide functionalities to keep track of nutritional consumption as well as to persuade users to change their eating behavior in positive ways. Also, group recommendation functionalities are very useful in the food domain, especially when a group of users wants to have a dinner together at home or have a birthday party in a restaurant. Such scenarios create many challenges for food recommender systems since the preferences of all group members have to be taken into account in an adequate fashion. In this paper, we present an overview of recommendation techniques for individuals and groups in the healthy food domain. In addition, we analyze the existing state-of-the-art in food recommender systems and discuss research challenges related to the development of future food recommendation technologies.
Social Navigation
Social Information Access, 2018
In this chapter we present one of the pioneer approaches in supporting users in navigating the complex information spaces, social navigation support. Social navigation support is inspired by natural tendencies of individuals to follow traces of each other in exploring the world, especially when dealing with uncertainties. In this chapter, we cover details on various approaches in implementing social navigation support in the information space as we also connect the concept to supporting theories. The first part of this chapter reviews related theories and introduces the design space of social navigation support through a series of example applications. The second part of the chapter discusses the common challenges in design and implementation of social navigation support, demonstrates how these challenges have been addressed, and reviews more recent direction of social navigation support. Furthermore, as social navigation support has been an inspirational approach to various other social information access approaches we discuss how social navigation support can be integrated with those approaches. We conclude with a review of evaluation methods for social navigation support and remarks about its current state.
Related papers
Food Recipe Recommendation System
mantech publications, 2023
In today's modern world everyone is so busy in their day to day life and in that hectic life sometime people tend to eat unhealthy fast food or food that has less nutritious value, everyone from a small business man to some owner of million-dollar company or a common man, everyone needs to eat food. Food is an essential for all human beings. This year pandemic of covid-19 has shown us eating healthy food is a must to keep ourselves fit. There is no food that can cure the virus of course but eating
A Socially-Aware Conversational Recommender System for Personalized Recipe Recommendations
Proceedings of the 8th International Conference on Human-Agent Interaction, 2020
One potential solution to help people change their eating behavior is to develop conversational systems able to recommend healthy recipes. Beyond the intrinsic quality of the recommendations themselves, various factors might also influence users' perception of a recommendation. Two of these factors are the conversational skills of the system and users' interaction modality. In this paper, we present Cora, a conversational system that recommends recipes aligned with its users' eating habits and current preferences. Users can interact with Cora in two different ways. They can select predefined answers by clicking on buttons to talk to Cora or write text in natural language. On the other hand, Cora can engage users through a social dialogue, or go straight to the point. We conduct an experiment to evaluate the impact of Cora's conversational skills and users' interaction mode on users' perception and intention to cook the recommended recipes. Our results show that a conversational recommendation system that engages its users through a rapport-building dialogue improves users' perception of the interaction as well as their perception of the system.
Social wisdom for search and recommendation
2008
Social-tagging communities offer great potential for smart recommendation and "socially enhanced" searchresult ranking. Beyond traditional forms of collaborative recommendation that are based on the item-user matrix of the entire community, a specific opportunity of social communities is to reflect the different degrees of friendships and mutual trust, in addition to the behavioral similarities among users. This paper presents a framework for harnessing such social relations for search and recommendation. The framework is implemented in the SENSE prototype system, and its usefulness is demonstrated in experiments with an excerpt of the librarything community data.
Social bookmarking and exploratory search
ESI 2007
In this paper, we explore various search tasks that are supported by a social bookmarking service. These bookmarking services hold great potential to powerfully combine personal tagging of information sources with interactive browsing, resulting in better social navigation. While there has been considerable interest in social tagging systems in recent years, little is known about their actual usage. In this paper, we present the results of a field study of a social bookmarking service that has been deployed in a large enterprise. We present new qualitative and quantitative data on how a corporate social tagging system was used, through both event logs (click level analysis) and interviews. We observed three types of search activities: community browsing, personal search, and explicit search. Community browsing was the most frequently used, and confirms the value of the social aspects of the system. We conclude that social bookmarking services support various kinds of exploratory search, and provide better personal bookmark management and enhance social navigation.
Sharing Social Recommendations: Towards a Social Portal
… Communities on the …, 2002
The Information Ecology project at DSTC is constructing a Social Portal. This article explains what we mean by a Social Portal, what user needs we believe we are serving by building one, what research goals we think we are serving and how we intend to go about it.
Social and collaborative web search
Proceedings of the 16th international conference on Intelligent user interfaces, 2011
In this paper we describe the results of a live-user study to demonstrate the benefits of using the social search utility HeyStaks, a novel approach to Web search that combines ideas from personalization and social networking to provide a more collaborative search experience.
Personalization of Supermarket Product Recommendations
Data Mining and Knowledge Discovery, 2001
We describe a personalized recommender system designed to suggest new products to supermarket shoppers. The recommender functions in a pervasive computing environment, namely, a remote shopping system in which supermarket customers use Personal Digital Assistants (PDAs) to compose and transmit their orders to the store, which assembles them for subsequent pickup. The recommender is meant to provide an alternative source of new ideas for customers who now visit the store less frequently. Recommendations are generated by matching products to customers based on the expected appeal of the product and the previous spending of the customer. Associations mining in the product domain is used to determine relationships among product classes for use in characterizing the appeal of individual products. Clustering in the customer domain is used to identify groups of shoppers with similar spending histories. Cluster-specific lists of popular products are then used as input to the matching process.
Commenders: A recommendation procedure for online book communities
Electronic Commerce Research and Applications, 2011
We propose a recommendation procedure for online book communities called ''Commenders.'' Its purpose is to enhance the effectiveness of community recommendation and also the satisfaction of individual members. The basic idea of our proposed approach is collaborative filtering (CF). It adapts a contentbased (CB) filtering algorithm by representing items with keyword features. The proposed recommendation procedure consists of two steps. During the first step, Commenders finds neighbors using community preferences for books and their feature information, and then it generates a CF-based recommendation list. The second step removes irrelevant books from the CF-based list using the keyword preferences of individual members. Commenders is designed to reduce individual member dissatisfaction with the process of finding desired books within an online community. To evaluate the procedure, we built a prototype system and performed experiments. Our experimental results show that the proposed system offers higher quality recommendations than the traditional collaborative filtering system. The proposed system has consistently higher precision, and individual members are more satisfied using this system.
Social bookmarking and information seeking
2008
In recent years, there has been tremendous growth in shared bookmarking applications. Introduced in 2003, the del. icio. us social bookmark website was one of the first of this kind of application, and has enjoyed an early and large base of committed users. A flurry of similar offerings has since been unveiled [see (Hammond, et al., 2005) for a recent review].
Using Tags and Latent Factors in a Food Recommender System
Due to the extensive growth of food varieties, making better and healthier food choices becomes more and more complex. Most of the current food suggestion applications offer just generic advices that are not tailored to personal taste. To tackle this issue, this paper proposes a novel food recommendation technology that provides high quality and personalized food suggestions based on user preference. Our evaluation results show that the proposed recommender significantly outperforms state-of-the-art algorithms by incorporating tags collected from users, which signal to the system the food's ingredients or features that the user likes. We have found that using tags in food recommendation algorithms can significantly increase the prediction accuracy, i.e., the match of the recommendations with the true user's preferred food. Furthermore, our user study shows that our system prototype is of high usability.
Loading Preview
Sorry, preview is currently unavailable. You can download the paper by clicking the button above.