The Netflix experience is driven by a number of recommendation algorithms: personalized ranking, page generation, similarity, ratings, search, etc. On the January 6th, 2016 we simultaneously launched Netflix in 130 new countries around the world, which brought the total to over 190 countries. Preparing for such a rapid expansion while ensuring each algorithm was ready to work seamlessly created new challenges for our recommendation and search teams. In this talk, we will highlight the four most interesting challenges we encountered in making our algorithms operate globally and how this improved our ability to connect members worldwide with stories they'll love. In particular, we will dive into the problems of uneven availability across catalogs, balancing personal and cultural tastes, handling language, and tracking quality of recommendations. Uneven catalog availability is a challenge because many recommendation algorithms assume that people could interact with any item and then use the absence of interaction implicitly or explicitly as negative information in the model. However, this assumption does not hold globally and across time where item availability differs. Running algorithms globally means needing a notion of location so that we can handle local variations in taste while also providing a good basis for personalization. Language is another challenge in recommending video content because people can typically only enjoy content that has assets (audio, subtitles) in languages they understand. The preferences for how people enjoy such content also vary between people and depend on their familiarity with a language. Also, while would like our recommendations to work well for every one of our members, tracking quality becomes difficult because with so many members in so many countries speaking so many languages, it can be hard to determine when an algorithm or system is performing sub-optimally for some subset of them. Thus, to support this global launch, we examined each and every algorithm that is part of our service and began to address these challenges.
{"title":"Recommending for the World","authors":"J. Basilico, Yves Raimond","doi":"10.1145/2959100.2959121","DOIUrl":"https://doi.org/10.1145/2959100.2959121","url":null,"abstract":"The Netflix experience is driven by a number of recommendation algorithms: personalized ranking, page generation, similarity, ratings, search, etc. On the January 6th, 2016 we simultaneously launched Netflix in 130 new countries around the world, which brought the total to over 190 countries. Preparing for such a rapid expansion while ensuring each algorithm was ready to work seamlessly created new challenges for our recommendation and search teams. In this talk, we will highlight the four most interesting challenges we encountered in making our algorithms operate globally and how this improved our ability to connect members worldwide with stories they'll love. In particular, we will dive into the problems of uneven availability across catalogs, balancing personal and cultural tastes, handling language, and tracking quality of recommendations. Uneven catalog availability is a challenge because many recommendation algorithms assume that people could interact with any item and then use the absence of interaction implicitly or explicitly as negative information in the model. However, this assumption does not hold globally and across time where item availability differs. Running algorithms globally means needing a notion of location so that we can handle local variations in taste while also providing a good basis for personalization. Language is another challenge in recommending video content because people can typically only enjoy content that has assets (audio, subtitles) in languages they understand. The preferences for how people enjoy such content also vary between people and depend on their familiarity with a language. Also, while would like our recommendations to work well for every one of our members, tracking quality becomes difficult because with so many members in so many countries speaking so many languages, it can be hard to determine when an algorithm or system is performing sub-optimally for some subset of them. Thus, to support this global launch, we examined each and every algorithm that is part of our service and began to address these challenges.","PeriodicalId":315651,"journal":{"name":"Proceedings of the 10th ACM Conference on Recommender Systems","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126488945","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}
Improving the performance of recommender systems using knowledge graphs is an important task. There have been many hybrid systems proposed in the past that use a mix of content-based and collaborative filtering techniques to boost the performance. More recently, some work has focused on recommendations that use external knowledge graphs (KGs) to supplement content-based recommendation. In this paper, we investigate three methods for making KG based recommendations using a general-purpose probabilistic logic system called ProPPR. The simplest of the models, EntitySim, uses only the links of the graph. We then extend the model to TypeSim that also uses the types of the entities to boost its generalization capabilities. Next, we develop a graph based latent factor model, GraphLF, which combines the strengths of latent factorization with graphs. We compare our approaches to a recently proposed state-of-the-art graph recommendation method on two large datasets, Yelp and MovieLens-100K. The experiments illustrate that our approaches can give large performance improvements. Additionally, we demonstrate that knowledge graphs give maximum advantage when the dataset is sparse, and gradually become redundant as more training data becomes available, and hence are most useful in cold-start settings.
{"title":"Personalized Recommendations using Knowledge Graphs: A Probabilistic Logic Programming Approach","authors":"R. Catherine, William W. Cohen","doi":"10.1145/2959100.2959131","DOIUrl":"https://doi.org/10.1145/2959100.2959131","url":null,"abstract":"Improving the performance of recommender systems using knowledge graphs is an important task. There have been many hybrid systems proposed in the past that use a mix of content-based and collaborative filtering techniques to boost the performance. More recently, some work has focused on recommendations that use external knowledge graphs (KGs) to supplement content-based recommendation. In this paper, we investigate three methods for making KG based recommendations using a general-purpose probabilistic logic system called ProPPR. The simplest of the models, EntitySim, uses only the links of the graph. We then extend the model to TypeSim that also uses the types of the entities to boost its generalization capabilities. Next, we develop a graph based latent factor model, GraphLF, which combines the strengths of latent factorization with graphs. We compare our approaches to a recently proposed state-of-the-art graph recommendation method on two large datasets, Yelp and MovieLens-100K. The experiments illustrate that our approaches can give large performance improvements. Additionally, we demonstrate that knowledge graphs give maximum advantage when the dataset is sparse, and gradually become redundant as more training data becomes available, and hence are most useful in cold-start settings.","PeriodicalId":315651,"journal":{"name":"Proceedings of the 10th ACM Conference on Recommender Systems","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128039224","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}
We bring to the fore of the recommender system research community, an inconvenient truth about the current state of understanding how recommender system algorithms and humans influence one another, both computationally and cognitively. Unlike the great variety of supervised machine learning algorithms which traditionally rely on expert input labels and are typically used for decision making by an expert, recommender systems specifically rely on data input from non-expert or casual users and are meant to be used directly by these same non-expert users on an every day basis. Furthermore, the advances in online machine learning, data generation, and predictive model learning have become increasingly interdependent, such that each one feeds on the other in an iterative cycle. Research in psychology suggests that people's choices are (1) contextually dependent, and (2) dependent on interaction history. Thus, while standard methods of training and assessing performance of recommender systems rely on benchmark datasets, we suggest that a critical step in the evolution of recommender systems is the development of benchmark models of human behavior that capture contextual and dynamic aspects of human behavior. It is important to emphasize that even extensive real life user-tests may not be sufficient to make up for this gap in benchmarking validity because user tests are typically done with either a focus on user satisfaction or engagement (clicks, sales, likes, etc) with whatever the recommender algorithm suggests to the user, and thus ignore the human cognitive aspect. We conclude by highlighting the interdisciplinary implications of this endeavor.
{"title":"Human-Recommender Systems: From Benchmark Data to Benchmark Cognitive Models","authors":"Patrick Shafto, O. Nasraoui","doi":"10.1145/2959100.2959188","DOIUrl":"https://doi.org/10.1145/2959100.2959188","url":null,"abstract":"We bring to the fore of the recommender system research community, an inconvenient truth about the current state of understanding how recommender system algorithms and humans influence one another, both computationally and cognitively. Unlike the great variety of supervised machine learning algorithms which traditionally rely on expert input labels and are typically used for decision making by an expert, recommender systems specifically rely on data input from non-expert or casual users and are meant to be used directly by these same non-expert users on an every day basis. Furthermore, the advances in online machine learning, data generation, and predictive model learning have become increasingly interdependent, such that each one feeds on the other in an iterative cycle. Research in psychology suggests that people's choices are (1) contextually dependent, and (2) dependent on interaction history. Thus, while standard methods of training and assessing performance of recommender systems rely on benchmark datasets, we suggest that a critical step in the evolution of recommender systems is the development of benchmark models of human behavior that capture contextual and dynamic aspects of human behavior. It is important to emphasize that even extensive real life user-tests may not be sufficient to make up for this gap in benchmarking validity because user tests are typically done with either a focus on user satisfaction or engagement (clicks, sales, likes, etc) with whatever the recommender algorithm suggests to the user, and thus ignore the human cognitive aspect. We conclude by highlighting the interdisciplinary implications of this endeavor.","PeriodicalId":315651,"journal":{"name":"Proceedings of the 10th ACM Conference on Recommender Systems","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133517054","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 evolution of the World Wide Web (WWW) and the smart-phone technologies have played a key role in the revolution of our daily life. The location-based social networks (LBSN) have emerged and facilitated the users to share the check-in information and multimedia contents. The Point of Interest (POI) recommendation system uses the check-in information to predict the most potential check-in locations. The different aspects of the check-in information, for instance, the geographical distance, the category, and the temporal popularity of a POI; and the temporal check-in trends, and the social (friendship) information of a user play a crucial role in an efficient recommendation. In this paper, we propose a fused recommendation model termed MAPS (Multi Aspect Personalized POI Recommender System) which will be the first in our knowledge to fuse the categorical, the temporal, the social and the spatial aspects in a single model. The major contribution of this paper are: (i) it realizes the problem as a graph of location nodes with constraints on the category and the distance aspects (i.e. the edge between two locations is constrained by a threshold distance and the category of the locations), (ii) it proposes a multi-aspect fused POI recommendation model, and (iii) it extensively evaluates the model with two real-world data sets.
万维网(WWW)和智能手机技术的发展在我们日常生活的变革中发挥了关键作用。基于位置的社交网络(LBSN)的出现为用户分享签到信息和多媒体内容提供了便利。兴趣点(POI)推荐系统使用登记信息来预测最有可能登记的地点。签到信息的不同方面，例如POI的地理距离、类别和时间流行度;用户的时间签到趋势和社交(友谊)信息在高效推荐中起着至关重要的作用。在本文中，我们提出了一个融合推荐模型，称为MAPS (Multi - Aspect Personalized POI Recommender System)，这将是我们所知的第一个将分类、时间、社会和空间方面融合在一个模型中的模型。本文的主要贡献是:(i)将问题实现为具有类别和距离约束的位置节点图(即两个位置之间的边缘受到阈值距离和位置类别的约束)，(ii)提出了一个多方面融合的POI推荐模型，(iii)使用两个真实数据集对模型进行了广泛的评估。
{"title":"MAPS: A Multi Aspect Personalized POI Recommender System","authors":"Ramesh Baral, Tao Li","doi":"10.1145/2959100.2959187","DOIUrl":"https://doi.org/10.1145/2959100.2959187","url":null,"abstract":"The evolution of the World Wide Web (WWW) and the smart-phone technologies have played a key role in the revolution of our daily life. The location-based social networks (LBSN) have emerged and facilitated the users to share the check-in information and multimedia contents. The Point of Interest (POI) recommendation system uses the check-in information to predict the most potential check-in locations. The different aspects of the check-in information, for instance, the geographical distance, the category, and the temporal popularity of a POI; and the temporal check-in trends, and the social (friendship) information of a user play a crucial role in an efficient recommendation. In this paper, we propose a fused recommendation model termed MAPS (Multi Aspect Personalized POI Recommender System) which will be the first in our knowledge to fuse the categorical, the temporal, the social and the spatial aspects in a single model. The major contribution of this paper are: (i) it realizes the problem as a graph of location nodes with constraints on the category and the distance aspects (i.e. the edge between two locations is constrained by a threshold distance and the category of the locations), (ii) it proposes a multi-aspect fused POI recommendation model, and (iii) it extensively evaluates the model with two real-world data sets.","PeriodicalId":315651,"journal":{"name":"Proceedings of the 10th ACM Conference on Recommender Systems","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126107115","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}
Ignacio Fernández-Tobías, Paolo Tomeo, Iván Cantador, T. D. Noia, E. Sciascio
Computing useful recommendations for cold-start users is a major challenge in the design of recommender systems, and additional data is often required to compensate the scarcity of user feedback. In this paper we address such problem in a target domain by exploiting user preferences from a related auxiliary domain. Following a rigorous methodology for cold-start, we evaluate a number of recommendation methods on a dataset with positive-only feedback in the movie and music domains, both in single and cross-domain scenarios. Comparing the methods in terms of item ranking accuracy, diversity and catalog coverage, we show that cross-domain preference data is useful to provide more accurate suggestions when user feedback in the target domain is scarce or not available at all, and may lead to more diverse recommendations depending on the target domain. Moreover, evaluating the impact of the user profile size and diversity in the source domain, we show that, in general, the quality of target recommendations increases with the size of the profile, but may deteriorate with too diverse profiles.
{"title":"Accuracy and Diversity in Cross-domain Recommendations for Cold-start Users with Positive-only Feedback","authors":"Ignacio Fernández-Tobías, Paolo Tomeo, Iván Cantador, T. D. Noia, E. Sciascio","doi":"10.1145/2959100.2959175","DOIUrl":"https://doi.org/10.1145/2959100.2959175","url":null,"abstract":"Computing useful recommendations for cold-start users is a major challenge in the design of recommender systems, and additional data is often required to compensate the scarcity of user feedback. In this paper we address such problem in a target domain by exploiting user preferences from a related auxiliary domain. Following a rigorous methodology for cold-start, we evaluate a number of recommendation methods on a dataset with positive-only feedback in the movie and music domains, both in single and cross-domain scenarios. Comparing the methods in terms of item ranking accuracy, diversity and catalog coverage, we show that cross-domain preference data is useful to provide more accurate suggestions when user feedback in the target domain is scarce or not available at all, and may lead to more diverse recommendations depending on the target domain. Moreover, evaluating the impact of the user profile size and diversity in the source domain, we show that, in general, the quality of target recommendations increases with the size of the profile, but may deteriorate with too diverse profiles.","PeriodicalId":315651,"journal":{"name":"Proceedings of the 10th ACM Conference on Recommender Systems","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128728359","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}
Over the recent years, a plethora of recommender systems (RS) have been proposed by academics. The degree of adoptability of these algorithms by industrial e-commerce platforms remains unclear. To get an insight into real-world recommendation engines, we survey more than 30 existing shopping cart solutions and compare the performance of popular recommendation algorithms on proprietary e-commerce datasets. Our results show that deployed systems rarely go beyond trivial "best seller" lists or very basic personalized recommendation algorithms, which nevertheless exhibit superior performance to more elaborate techniques both in our experiments and other related studies. We also perform chronological dataset splits to demonstrate the importance of preserving the sequence of events during evaluation, and the recency of events during training. The second part of our research is still ongoing and focuses on various ethical challenges that complicate the design of recommender systems. We believe that this direction of research remains mostly neglected despite its increasing impact on RS' quality and safety.
{"title":"Recommender Systems from an Industrial and Ethical Perspective","authors":"Dimitris Paraschakis","doi":"10.1145/2959100.2959101","DOIUrl":"https://doi.org/10.1145/2959100.2959101","url":null,"abstract":"Over the recent years, a plethora of recommender systems (RS) have been proposed by academics. The degree of adoptability of these algorithms by industrial e-commerce platforms remains unclear. To get an insight into real-world recommendation engines, we survey more than 30 existing shopping cart solutions and compare the performance of popular recommendation algorithms on proprietary e-commerce datasets. Our results show that deployed systems rarely go beyond trivial \"best seller\" lists or very basic personalized recommendation algorithms, which nevertheless exhibit superior performance to more elaborate techniques both in our experiments and other related studies. We also perform chronological dataset splits to demonstrate the importance of preserving the sequence of events during evaluation, and the recency of events during training. The second part of our research is still ongoing and focuses on various ethical challenges that complicate the design of recommender systems. We believe that this direction of research remains mostly neglected despite its increasing impact on RS' quality and safety.","PeriodicalId":315651,"journal":{"name":"Proceedings of the 10th ACM Conference on Recommender Systems","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121800232","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}
This turorial offers a rich blend of theory and practice regarding dimensionality reduction methods, to address the information overload problem in recommender systems. This problem affects our everyday experience while searching for knowledge on a topic. Naive Collaborative Filtering cannot deal with challenging issues such as scalability, noise, and sparsity. We can deal with all the aforementioned challenges by applying matrix and tensor decomposition methods. These methods have been proven to be the most accurate (i.e., Netflix prize) and efficient for handling big data. For each method (SVD, SVD++, timeSVD++, HOSVD, CUR, etc.) we will provide a detailed theoretical mathematical background and a step-by-step analysis, by using an integrated toy example, which runs throughout all parts of the tutorial, helping the audience to understand clearly the differences among factorisation methods.
{"title":"Matrix and Tensor Decomposition in Recommender Systems","authors":"P. Symeonidis","doi":"10.1145/2959100.2959195","DOIUrl":"https://doi.org/10.1145/2959100.2959195","url":null,"abstract":"This turorial offers a rich blend of theory and practice regarding dimensionality reduction methods, to address the information overload problem in recommender systems. This problem affects our everyday experience while searching for knowledge on a topic. Naive Collaborative Filtering cannot deal with challenging issues such as scalability, noise, and sparsity. We can deal with all the aforementioned challenges by applying matrix and tensor decomposition methods. These methods have been proven to be the most accurate (i.e., Netflix prize) and efficient for handling big data. For each method (SVD, SVD++, timeSVD++, HOSVD, CUR, etc.) we will provide a detailed theoretical mathematical background and a step-by-step analysis, by using an integrated toy example, which runs throughout all parts of the tutorial, helping the audience to understand clearly the differences among factorisation methods.","PeriodicalId":315651,"journal":{"name":"Proceedings of the 10th ACM Conference on Recommender Systems","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124473202","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}
Conformity has a strong influence to user behaviors, even in online environment. When surfing online, users are usually flooded with others' opinions. These opinions implicitly contribute to the user's ongoing behaviors. However, there is no research work modeling online conformity yet. In this paper, we model user's conformity in online rating sites. We conduct analysis using real data to show the existence and strength of conformity in these scenarios. We propose a matrix-factorization-based conformity modeling technique to improve the accuracy of rating prediction. Experiments show that our model outperforms existing works significantly (with a relative improvement of 11.72% on RMSE). Therefore, we draw the conclusion that conformity modeling is important for understanding user behaviors and can contribute to further improve the online recommender systems.
{"title":"Are You Influenced by Others When Rating?: Improve Rating Prediction by Conformity Modeling","authors":"Yiming Liu, Xuezhi Cao, Yong Yu","doi":"10.1145/2959100.2959141","DOIUrl":"https://doi.org/10.1145/2959100.2959141","url":null,"abstract":"Conformity has a strong influence to user behaviors, even in online environment. When surfing online, users are usually flooded with others' opinions. These opinions implicitly contribute to the user's ongoing behaviors. However, there is no research work modeling online conformity yet. In this paper, we model user's conformity in online rating sites. We conduct analysis using real data to show the existence and strength of conformity in these scenarios. We propose a matrix-factorization-based conformity modeling technique to improve the accuracy of rating prediction. Experiments show that our model outperforms existing works significantly (with a relative improvement of 11.72% on RMSE). Therefore, we draw the conclusion that conformity modeling is important for understanding user behaviors and can contribute to further improve the online recommender systems.","PeriodicalId":315651,"journal":{"name":"Proceedings of the 10th ACM Conference on Recommender Systems","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114567992","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 purpose of Recommender Systems is to minimize the effects of information/choice overload. Recommendations are usually prepared based on the estimation of what would be useful or interesting to users. Thus, it is important that they are relevant to users, whether to their information needs, current activity or emotional state. This requires deep understanding of users' context but also the knowledge of the history of previous users' interactions within the system (e.g. clicks, views, etc.). But even when the recommendations are highly relevant, their delivery to users can be very problematic. Many existing systems require active user participation (explicit interaction with the recommender system) and attention. Or, on other side of spectrum, there are RS that handle recommendation delivery without any consideration for users' preferences of when, where or how the recommendations are being delivered. Proactive Recommender Systems promise a more autonomous approach for recommendation delivery, by anticipating information needs in advance and acting on users' behalf with minimal efforts and without disturbance. This paper describes our work and interest in identifying and analyzing the factors that can influence acceptance and use of proactively delivered recommendations.
{"title":"Proactive Recommendation Delivery","authors":"Adem Sabic","doi":"10.1145/2959100.2959108","DOIUrl":"https://doi.org/10.1145/2959100.2959108","url":null,"abstract":"The main purpose of Recommender Systems is to minimize the effects of information/choice overload. Recommendations are usually prepared based on the estimation of what would be useful or interesting to users. Thus, it is important that they are relevant to users, whether to their information needs, current activity or emotional state. This requires deep understanding of users' context but also the knowledge of the history of previous users' interactions within the system (e.g. clicks, views, etc.). But even when the recommendations are highly relevant, their delivery to users can be very problematic. Many existing systems require active user participation (explicit interaction with the recommender system) and attention. Or, on other side of spectrum, there are RS that handle recommendation delivery without any consideration for users' preferences of when, where or how the recommendations are being delivered. Proactive Recommender Systems promise a more autonomous approach for recommendation delivery, by anticipating information needs in advance and acting on users' behalf with minimal efforts and without disturbance. This paper describes our work and interest in identifying and analyzing the factors that can influence acceptance and use of proactively delivered recommendations.","PeriodicalId":315651,"journal":{"name":"Proceedings of the 10th ACM Conference on Recommender Systems","volume":"25 2A 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133311030","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}
We address the challenge of personalized recommendation of high quality content producers in social media. While some candidates are easily identifiable (say, by being "favorited" many times), there is a long-tail of potential candidates for whom we have little evidence. Through careful modeling of contextual factors like the geo-spatial, topical, and social preferences of users, we propose a tensor-based personalized expert recommendation framework that integrates these factors for revealing latent connections between homogeneous entities (e.g., users and users) and between heterogeneous entities (e.g., users and experts). Through extensive experiments over geo-tagged Twitter data, we find that the proposed framework can improve the quality of recommendation by over 30% in both precision and recall compared to the state-of-the-art.
{"title":"TAPER: A Contextual Tensor-Based Approach for Personalized Expert Recommendation","authors":"Hancheng Ge, James Caverlee, Haokai Lu","doi":"10.1145/2959100.2959151","DOIUrl":"https://doi.org/10.1145/2959100.2959151","url":null,"abstract":"We address the challenge of personalized recommendation of high quality content producers in social media. While some candidates are easily identifiable (say, by being \"favorited\" many times), there is a long-tail of potential candidates for whom we have little evidence. Through careful modeling of contextual factors like the geo-spatial, topical, and social preferences of users, we propose a tensor-based personalized expert recommendation framework that integrates these factors for revealing latent connections between homogeneous entities (e.g., users and users) and between heterogeneous entities (e.g., users and experts). Through extensive experiments over geo-tagged Twitter data, we find that the proposed framework can improve the quality of recommendation by over 30% in both precision and recall compared to the state-of-the-art.","PeriodicalId":315651,"journal":{"name":"Proceedings of the 10th ACM Conference on Recommender Systems","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122155947","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：