One of the most significant map services in navigation applications is route recommendation. However, most route recommendation systems only recommend trips based on time and distance, impacting quality-of-experience and route selection. This paper introduces a novel framework, namely MARRS, a multi-objective route recommendation system based on heterogeneous urban sensing open data (i.e., crime, accident, traffic flow, road network, meteorological, calendar event, and point of interest distributions). We introduce a wide, deep, and multitask-learning (WD-MTL) framework that uses a transformer to extract spatial, temporal, and semantic correlation for predicting crime, accident, and traffic flow of particular road segment. Later, for a particular source and destination, the adaptive epsilon constraint technique is used to optimize route satisfying multiple objective functions. The experimental results demonstrate the feasibility of figuring out the safest and efficient route selection.
{"title":"MARRS: A Framework for multi-objective risk-aware route recommendation using Multitask-Transformer","authors":"Bhumika, D. Das","doi":"10.1145/3523227.3546787","DOIUrl":"https://doi.org/10.1145/3523227.3546787","url":null,"abstract":"One of the most significant map services in navigation applications is route recommendation. However, most route recommendation systems only recommend trips based on time and distance, impacting quality-of-experience and route selection. This paper introduces a novel framework, namely MARRS, a multi-objective route recommendation system based on heterogeneous urban sensing open data (i.e., crime, accident, traffic flow, road network, meteorological, calendar event, and point of interest distributions). We introduce a wide, deep, and multitask-learning (WD-MTL) framework that uses a transformer to extract spatial, temporal, and semantic correlation for predicting crime, accident, and traffic flow of particular road segment. Later, for a particular source and destination, the adaptive epsilon constraint technique is used to optimize route satisfying multiple objective functions. The experimental results demonstrate the feasibility of figuring out the safest and efficient route selection.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124670363","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Evaluating recommendation systems is a task of utmost importance and a very active research field. While online evaluation is the most reliable evaluation procedure, it may also be too expensive to perform, if not unfeasible. Therefore, researchers and practitioners resort to offline evaluation. Offline evaluation is much more efficient and scalable, but traditional approaches suffer from high bias. This issue led to the increased popularity of counterfactual techniques. These techniques are used for evaluation and learning in recommender systems and reduce the bias in offline evaluation. While counterfactual approaches have a solid statistical basis, their application to recommendation systems is still in a preliminary research phase. In this paper, we identify some limitations of counterfactual techniques applied to recommender systems, and we propose possible ways to overcome them.
{"title":"Enhancing Counterfactual Evaluation and Learning for Recommendation Systems","authors":"Nicolò Felicioni","doi":"10.1145/3523227.3547429","DOIUrl":"https://doi.org/10.1145/3523227.3547429","url":null,"abstract":"Evaluating recommendation systems is a task of utmost importance and a very active research field. While online evaluation is the most reliable evaluation procedure, it may also be too expensive to perform, if not unfeasible. Therefore, researchers and practitioners resort to offline evaluation. Offline evaluation is much more efficient and scalable, but traditional approaches suffer from high bias. This issue led to the increased popularity of counterfactual techniques. These techniques are used for evaluation and learning in recommender systems and reduce the bias in offline evaluation. While counterfactual approaches have a solid statistical basis, their application to recommendation systems is still in a preliminary research phase. In this paper, we identify some limitations of counterfactual techniques applied to recommender systems, and we propose possible ways to overcome them.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127378069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Making recommender systems more transparent and auditable is crucial for the future adoption of these systems. Available tools typically present mostly errors of models aggregated over all test users, which is often insufficient to uncover hidden biases and problems. Moreover, the emphasis is primarily on the accuracy of recommendations but less on other important metrics, such as the diversity of recommended items, the extent of catalog coverage, or the opportunity to discover novel items at bestsellers’ expense. In this work, we propose RepSys, a framework for evaluating recommender systems. Our work offers a set of highly interactive approaches for investigating various scenario recommendations, analyzing a dataset, and evaluating distributions of various metrics that combine visualization techniques with existing offline evaluation methods. RepSys framework is available under an open-source license to other researchers.
{"title":"RepSys: Framework for Interactive Evaluation of Recommender Systems","authors":"J. Safarik, Vojtěch Vančura, P. Kordík","doi":"10.1145/3523227.3551469","DOIUrl":"https://doi.org/10.1145/3523227.3551469","url":null,"abstract":"Making recommender systems more transparent and auditable is crucial for the future adoption of these systems. Available tools typically present mostly errors of models aggregated over all test users, which is often insufficient to uncover hidden biases and problems. Moreover, the emphasis is primarily on the accuracy of recommendations but less on other important metrics, such as the diversity of recommended items, the extent of catalog coverage, or the opportunity to discover novel items at bestsellers’ expense. In this work, we propose RepSys, a framework for evaluating recommender systems. Our work offers a set of highly interactive approaches for investigating various scenario recommendations, analyzing a dataset, and evaluating distributions of various metrics that combine visualization techniques with existing offline evaluation methods. RepSys framework is available under an open-source license to other researchers.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121227317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tzoof Avny Brosh, Amit Livne, Oren Sar Shalom, Bracha Shapira, Mark Last
A bundle is a pre-defined set of items that are collected together. In many domains, bundling is one of the most important marketing strategies for item promotion, commonly used in e-commerce. Bundle recommendation resembles the item recommendation task, where bundles are the recommended unit, but it poses additional challenges; while item recommendation requires only user and item understanding, bundle recommendation also requires modeling the connections between the various items in a bundle. Transformers have driven the state-of-the-art methods for set and sequence modeling in various natural language processing and computer vision tasks, emphasizing the understanding that the neighbors of an element are of crucial importance. Under some required adjustments, we believe the same applies for items in bundles, and better capturing the relations of an item with other items in the bundle may lead to improved recommendations. To address that, we introduce BRUCE - a novel model for bundle recommendation, in which we adapt Transformers to represent data on users, items, and bundles. This allows exploiting the self-attention mechanism to model the following: latent relations between the items in a bundle; and users’ preferences toward each of the items in the bundle and toward the whole bundle. Moreover, we examine various architectures to integrate the items’ and the users’ information and provide insights on architecture selection based on data characteristics. Experiments conducted on three benchmark datasets show that the proposed approach contributes to the accuracy of the recommendation and substantially outperforms state-of-the-art methods
{"title":"BRUCE: Bundle Recommendation Using Contextualized item Embeddings","authors":"Tzoof Avny Brosh, Amit Livne, Oren Sar Shalom, Bracha Shapira, Mark Last","doi":"10.1145/3523227.3546754","DOIUrl":"https://doi.org/10.1145/3523227.3546754","url":null,"abstract":"A bundle is a pre-defined set of items that are collected together. In many domains, bundling is one of the most important marketing strategies for item promotion, commonly used in e-commerce. Bundle recommendation resembles the item recommendation task, where bundles are the recommended unit, but it poses additional challenges; while item recommendation requires only user and item understanding, bundle recommendation also requires modeling the connections between the various items in a bundle. Transformers have driven the state-of-the-art methods for set and sequence modeling in various natural language processing and computer vision tasks, emphasizing the understanding that the neighbors of an element are of crucial importance. Under some required adjustments, we believe the same applies for items in bundles, and better capturing the relations of an item with other items in the bundle may lead to improved recommendations. To address that, we introduce BRUCE - a novel model for bundle recommendation, in which we adapt Transformers to represent data on users, items, and bundles. This allows exploiting the self-attention mechanism to model the following: latent relations between the items in a bundle; and users’ preferences toward each of the items in the bundle and toward the whole bundle. Moreover, we examine various architectures to integrate the items’ and the users’ information and provide insights on architecture selection based on data characteristics. Experiments conducted on three benchmark datasets show that the proposed approach contributes to the accuracy of the recommendation and substantially outperforms state-of-the-art methods","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122680665","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Vojtěch Vančura, Rodrigo Alves, Petr Kasalický, P. Kordík
Recently, the RS research community has witnessed a surge in popularity for shallow autoencoder-based CF methods. Due to its straightforward implementation and high accuracy on item retrieval metrics, EASE is potentially the most prominent of these models. Despite its accuracy and simplicity, EASE cannot be employed in some real-world recommender system applications due to its inability to scale to huge interaction matrices. In this paper, we proposed ELSA, a scalable shallow autoencoder method for implicit feedback recommenders. ELSA is a scalable autoencoder in which the hidden layer is factorizable into a low-rank plus sparse structure, thereby drastically lowering memory consumption and computation time. We conducted a comprehensive offline experimental section that combined synthetic and several real-world datasets. We also validated our strategy in an online setting by comparing ELSA to baselines in a live recommender system using an A/B test. Experiments demonstrate that ELSA is scalable and has competitive performance. Finally, we demonstrate the explainability of ELSA by illustrating the recovered latent space.
{"title":"Scalable Linear Shallow Autoencoder for Collaborative Filtering","authors":"Vojtěch Vančura, Rodrigo Alves, Petr Kasalický, P. Kordík","doi":"10.1145/3523227.3551482","DOIUrl":"https://doi.org/10.1145/3523227.3551482","url":null,"abstract":"Recently, the RS research community has witnessed a surge in popularity for shallow autoencoder-based CF methods. Due to its straightforward implementation and high accuracy on item retrieval metrics, EASE is potentially the most prominent of these models. Despite its accuracy and simplicity, EASE cannot be employed in some real-world recommender system applications due to its inability to scale to huge interaction matrices. In this paper, we proposed ELSA, a scalable shallow autoencoder method for implicit feedback recommenders. ELSA is a scalable autoencoder in which the hidden layer is factorizable into a low-rank plus sparse structure, thereby drastically lowering memory consumption and computation time. We conducted a comprehensive offline experimental section that combined synthetic and several real-world datasets. We also validated our strategy in an online setting by comparing ELSA to baselines in a live recommender system using an A/B test. Experiments demonstrate that ELSA is scalable and has competitive performance. Finally, we demonstrate the explainability of ELSA by illustrating the recovered latent space.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132414052","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
G. Adomavicius, Konstantin Bauman, B. Mobasher, Francesco Ricci, Alexander Tuzhilin, Moshe Unger
Contextual information has been widely recognized as an important modeling dimension in social sciences and in computing. In particular, the role of context has been recognized in enhancing recommendation results and retrieval performance. While a substantial amount of existing research has focused on context-aware recommender systems (CARS), many interesting problems remain under-explored. The CARS 2022 workshop provides a venue for presenting and discussing: the important features of the next generation of CARS; and application domains that may require the use of novel types of contextual information and cope with their dynamic properties in group recommendations and in online environments.
{"title":"CARS: Workshop on Context-Aware Recommender Systems 2022","authors":"G. Adomavicius, Konstantin Bauman, B. Mobasher, Francesco Ricci, Alexander Tuzhilin, Moshe Unger","doi":"10.1145/3523227.3547421","DOIUrl":"https://doi.org/10.1145/3523227.3547421","url":null,"abstract":"Contextual information has been widely recognized as an important modeling dimension in social sciences and in computing. In particular, the role of context has been recognized in enhancing recommendation results and retrieval performance. While a substantial amount of existing research has focused on context-aware recommender systems (CARS), many interesting problems remain under-explored. The CARS 2022 workshop provides a venue for presenting and discussing: the important features of the next generation of CARS; and application domains that may require the use of novel types of contextual information and cope with their dynamic properties in group recommendations and in online environments.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127007846","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The main source of knowledge utilized in recommender systems (RS) is users’ feedback. While the usage of implicit feedback (i.e. user’s behavior statistics) is gaining in prominence, the explicit feedback (i.e. user’s ratings) remain an important data source. This is true especially for domains, where evaluation of an object does not require an extensive usage and users are well motivated to do so (e.g., video-on-demand services or library archives). So far, numerous rating schemes for explicit feedback have been proposed, ranging both in granularity and presentation style. There are several works studying the effect of rating’s scale and presentation on user’s rating behavior, e.g. willingness to provide feedback or various biases in rating behavior. Nonetheless, the effect of ratings granularity on RS performance remain largely under-researched. In this paper, we studied the combined effect of ratings granularity and supposed probability of feedback existence on various performance statistics of recommender systems. Results indicate that decreasing feedback granularity may lead to changes in RS’s performance w.r.t. nDCG for some recommending algorithms. Nonetheless, in most cases the effect of feedback granularity is surpassed by even a small decrease in feedback’s quantity. Therefore, our results corroborate the policy of many major real-world applications, i.e. preference of simpler rating schemes with the higher chance of feedback reception instead of finer-grained rating scenarios.
{"title":"The Effect of Feedback Granularity on Recommender Systems Performance","authors":"Ladislav Peška, Stepán Balcar","doi":"10.1145/3523227.3551479","DOIUrl":"https://doi.org/10.1145/3523227.3551479","url":null,"abstract":"The main source of knowledge utilized in recommender systems (RS) is users’ feedback. While the usage of implicit feedback (i.e. user’s behavior statistics) is gaining in prominence, the explicit feedback (i.e. user’s ratings) remain an important data source. This is true especially for domains, where evaluation of an object does not require an extensive usage and users are well motivated to do so (e.g., video-on-demand services or library archives). So far, numerous rating schemes for explicit feedback have been proposed, ranging both in granularity and presentation style. There are several works studying the effect of rating’s scale and presentation on user’s rating behavior, e.g. willingness to provide feedback or various biases in rating behavior. Nonetheless, the effect of ratings granularity on RS performance remain largely under-researched. In this paper, we studied the combined effect of ratings granularity and supposed probability of feedback existence on various performance statistics of recommender systems. Results indicate that decreasing feedback granularity may lead to changes in RS’s performance w.r.t. nDCG for some recommending algorithms. Nonetheless, in most cases the effect of feedback granularity is surpassed by even a small decrease in feedback’s quantity. Therefore, our results corroborate the policy of many major real-world applications, i.e. preference of simpler rating schemes with the higher chance of feedback reception instead of finer-grained rating scenarios.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126898195","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Minmin Chen, Can Xu, Vince Gatto, Devanshu Jain, Aviral Kumar, Ed H. Chi
Industrial recommendation platforms are increasingly concerned with how to make recommendations that cause users to enjoy their long term experience on the platform. Reinforcement learning emerged naturally as an appealing approach for its promise in 1) combating feedback loop effect resulted from myopic system behaviors; and 2) sequential planning to optimize long term outcome. Scaling RL algorithms to production recommender systems serving billions of users and contents, however remain challenging. Sample inefficiency and instability of online RL hinder its widespread adoption in production. Offline RL enables usage of off-policy data and batch learning. It on the other hand faces significant challenges in learning due to the distribution shift. A REINFORCE agent [3] was successfully tested for YouTube recommendation, significantly outperforming a sophisticated supervised learning production system. Off-policy correction was employed to learn from logged data. The algorithm partially mitigates the distribution shift by employing a one-step importance weighting. We resort to the off-policy actor critic algorithms to addresses the distribution shift to a better extent. Here we share the key designs in setting up an off-policy actor-critic agent for production recommender systems. It extends [3] with a critic network that estimates the value of any state-action pairs under the target learned policy through temporal difference learning. We demonstrate in offline and live experiments that the new framework out-performs baseline and improves long term user experience. An interesting discovery along our investigation is that recommendation agents that employ a softmax policy parameterization, can end up being too pessimistic about out-of-distribution (OOD) actions. Finding the right balance between pessimism and optimism on OOD actions is critical to the success of offline RL for recommender systems.
{"title":"Off-Policy Actor-critic for Recommender Systems","authors":"Minmin Chen, Can Xu, Vince Gatto, Devanshu Jain, Aviral Kumar, Ed H. Chi","doi":"10.1145/3523227.3546758","DOIUrl":"https://doi.org/10.1145/3523227.3546758","url":null,"abstract":"Industrial recommendation platforms are increasingly concerned with how to make recommendations that cause users to enjoy their long term experience on the platform. Reinforcement learning emerged naturally as an appealing approach for its promise in 1) combating feedback loop effect resulted from myopic system behaviors; and 2) sequential planning to optimize long term outcome. Scaling RL algorithms to production recommender systems serving billions of users and contents, however remain challenging. Sample inefficiency and instability of online RL hinder its widespread adoption in production. Offline RL enables usage of off-policy data and batch learning. It on the other hand faces significant challenges in learning due to the distribution shift. A REINFORCE agent [3] was successfully tested for YouTube recommendation, significantly outperforming a sophisticated supervised learning production system. Off-policy correction was employed to learn from logged data. The algorithm partially mitigates the distribution shift by employing a one-step importance weighting. We resort to the off-policy actor critic algorithms to addresses the distribution shift to a better extent. Here we share the key designs in setting up an off-policy actor-critic agent for production recommender systems. It extends [3] with a critic network that estimates the value of any state-action pairs under the target learned policy through temporal difference learning. We demonstrate in offline and live experiments that the new framework out-performs baseline and improves long term user experience. An interesting discovery along our investigation is that recommendation agents that employ a softmax policy parameterization, can end up being too pessimistic about out-of-distribution (OOD) actions. Finding the right balance between pessimism and optimism on OOD actions is critical to the success of offline RL for recommender systems.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125379971","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. Konstan, A. Muralidharan, Ankan Saha, Shilad Sen, Mengting Wan, Longqi Yang
As organizations increasingly digitize their business processes, the role of recommender systems in work environments is expanding. The goal of the RecWork workshop is closing the gap in recommender systems research for work environments in areas such as calendaring, productivity, community building, space planning, workforce development, and information routing. RecWork will bring together experts who will collaboratively synthesize a forward-looking research agenda for recommender systems in the workplace. The outcome will be captured through a white paper that will serve as the foundation for future RecWork workshops. These steps will help advance research in workplace recommenders and broaden the reach of the RecSys conference.
{"title":"RecWork: Workshop on Recommender Systems for the Future of Work","authors":"J. Konstan, A. Muralidharan, Ankan Saha, Shilad Sen, Mengting Wan, Longqi Yang","doi":"10.1145/3523227.3547415","DOIUrl":"https://doi.org/10.1145/3523227.3547415","url":null,"abstract":"As organizations increasingly digitize their business processes, the role of recommender systems in work environments is expanding. The goal of the RecWork workshop is closing the gap in recommender systems research for work environments in areas such as calendaring, productivity, community building, space planning, workforce development, and information routing. RecWork will bring together experts who will collaboratively synthesize a forward-looking research agenda for recommender systems in the workplace. The outcome will be captured through a white paper that will serve as the foundation for future RecWork workshops. These steps will help advance research in workplace recommenders and broaden the reach of the RecSys conference.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121495837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Recommender systems are used in many different applications and contexts, however their main goal can always be summarised as “connecting relevant content to interested users”. Explanations have been found to help recommender systems achieve this goal by giving users a look under the hood that helps them understand why they are recommended certain items. Furthermore, explanations can be considered to be the first step towards interacting with the system. Indeed, for a user to give feedback and guide the system towards better understanding her preferences, it helps if the user has a better idea of what the system has already learned. To this end, we propose a linear collaborative filtering recommendation model that builds user profiles within the domain of item metadata. Our method is hence inherently transparent and explainable. Moreover, since recommendations are computed as a linear function of item metadata and the interpretable user profile, our method seamlessly supports interactive recommendation. In other words, users can directly tweak the weights of the learned profile for more fine-grained browsing and discovery of content based on their current interests. We demonstrate the interactive aspect of this model in an online application for discovering cultural events in Belgium.
{"title":"Who do you think I am? Interactive User Modelling with Item Metadata","authors":"Joey De Pauw, Koen Ruymbeek, Bart Goethals","doi":"10.1145/3523227.3551470","DOIUrl":"https://doi.org/10.1145/3523227.3551470","url":null,"abstract":"Recommender systems are used in many different applications and contexts, however their main goal can always be summarised as “connecting relevant content to interested users”. Explanations have been found to help recommender systems achieve this goal by giving users a look under the hood that helps them understand why they are recommended certain items. Furthermore, explanations can be considered to be the first step towards interacting with the system. Indeed, for a user to give feedback and guide the system towards better understanding her preferences, it helps if the user has a better idea of what the system has already learned. To this end, we propose a linear collaborative filtering recommendation model that builds user profiles within the domain of item metadata. Our method is hence inherently transparent and explainable. Moreover, since recommendations are computed as a linear function of item metadata and the interpretable user profile, our method seamlessly supports interactive recommendation. In other words, users can directly tweak the weights of the learned profile for more fine-grained browsing and discovery of content based on their current interests. We demonstrate the interactive aspect of this model in an online application for discovering cultural events in Belgium.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116371430","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}