Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization最新文献_第2页

Analyzing and Predicting Task Reminders 分析和预测任务提醒

Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization Pub Date : 2016-07-13 DOI: 10.1145/2930238.2930239

David Graus, Paul N. Bennett, Ryen W. White, E. Horvitz

{"title":"Analyzing and Predicting Task Reminders","authors":"David Graus, Paul N. Bennett, Ryen W. White, E. Horvitz","doi":"10.1145/2930238.2930239","DOIUrl":"https://doi.org/10.1145/2930238.2930239","url":null,"abstract":"Automated personal assistants such as Siri, Cortana, and Google Now provide services to help users accomplish tasks, including tools to set reminders. We study how people specify and use reminders. Our study analyzes a sample of six months of logs of user-specified reminders from Cortana (Microsoft's intelligent personal assistant), the first large-scale analysis of such reminders. We focus our analyses on time-based reminders, the most common type of reminder found in the logs. We perform a data-driven analysis to identify common categories of tasks that give rise to these reminders across a large number of users, and we arrange these tasks into a taxonomy. We identify temporal patterns linked to the type of task, time of creation, and terms in the reminder text. Finally, we show that these patterns generalize by addressing a prediction task. Specifically, we show that a reminder's creation time is a strong feature in predicting the notification time, and that including the reminder text further improves prediction accuracy. The results have implications for the design of systems aimed at helping people to complete tasks and to plan future activities.","PeriodicalId":339100,"journal":{"name":"Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125529745","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}

引用次数: 35

From More-Like-This to Better-Than-This: Hotel Recommendations from User Generated Reviews 从更像这个到比这个更好:来自用户评论的酒店推荐

Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization Pub Date : 2016-07-13 DOI: 10.1145/2930238.2930276

Ruihai Dong, Barry Smyth

引用次数: 11

Incorporating Student Response Time and Tutor Instructional Interventions into Student Modeling 将学生反应时间和导师教学干预纳入学生建模

Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization Pub Date : 2016-07-13 DOI: 10.1145/2930238.2930291

Chen Lin, Shitian Shen, Min Chi

引用次数: 21

Plate and Prejudice: Gender Differences in Online Cooking 盘子与偏见:网上烹饪的性别差异

Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization Pub Date : 2016-07-13 DOI: 10.1145/2930238.2930248

Markus Rokicki, E. Herder, T. Kusmierczyk, C. Trattner

引用次数: 26

Relating Newcomer Personality to Survival and Activity in Recommender Systems 将新人的个性与推荐系统中的生存和活动联系起来

Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization Pub Date : 2016-07-13 DOI: 10.1145/2930238.2930246

Raghav Pavan Karumur, J. Konstan

{"title":"Relating Newcomer Personality to Survival and Activity in Recommender Systems","authors":"Raghav Pavan Karumur, J. Konstan","doi":"10.1145/2930238.2930246","DOIUrl":"https://doi.org/10.1145/2930238.2930246","url":null,"abstract":"In this work, we explore the degree to which personality information can be used to model newcomer retention, investment, intensity of engagement, and distribution of activity in a recommender community. Prior work shows that Big-Five Personality traits can explain variation in user behavior in other contexts. Building on this, we carry out and report on an analysis of 1008 MovieLens users with identified personality profiles. We find that Introverts and low Agreeableness users are more likely to survive into the second and subsequent sessions compared to their respective counterparts; Introverts and low Conscientiousness users are a significantly more active population compared to their respective counterparts; High Openness and High Neuroticism users contribute (tag) significantly more compared to their counterparts, but their counterparts consume (browse and bookmark) more; and low Agreeableness users are more likely to rate whereas high Agreeableness users are more likely to tag. These results show how modeling newcomer behavior from user personality can be useful for recommender systems designers as they customize the system to guide people towards tasks that need to be done or tasks the users will find rewarding and also decide which users to invest retention efforts in.","PeriodicalId":339100,"journal":{"name":"Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131604825","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}

引用次数: 5

Modeling and Predicting User Actions in Recommender Systems 在推荐系统中建模和预测用户行为

Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization Pub Date : 2016-07-13 DOI: 10.1145/2930238.2930284

Tural Gurbanov, F. Ricci, M. Ploner

{"title":"Modeling and Predicting User Actions in Recommender Systems","authors":"Tural Gurbanov, F. Ricci, M. Ploner","doi":"10.1145/2930238.2930284","DOIUrl":"https://doi.org/10.1145/2930238.2930284","url":null,"abstract":"Many collaborative filtering recommender systems collect and use users' explicitly entered preferences in the form of ratings for items. However, in many real world scenarios, this form of feedback can be difficult to obtain or unavailable (e.g., news portals). In this case recommendations must be built by leveraging more abundant implicit feedback data, which only indirectly signal users' preferences or opinions. A record in such datasets is a result of an action performed by a user on an item (e.g., the item was clicked or viewed). State-of-the-art implicit feedback recommender systems predict whether the user will act on a target item and interpret this prediction as a discovered preference for the item. These models are trained by observations of user actions of one single type. For instance, they predict that a user will watch a video using a dataset of observed video watch actions. In this paper we conjecture that multiple types of user actions may be jointly exploited to predict one target type of actions. We present a general prediction model (MMF - Multiple action types Matrix Factorization) that implements this conjecture and we illustrate some practical examples. The empirical evaluation of MMF, which was conducted on a large real world dataset, shows that using multiple actions is beneficial and it can outperform a state-of-the-art implicit feedback model that uses only the target action data.","PeriodicalId":339100,"journal":{"name":"Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127207711","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}

引用次数: 8

Predicting Individual Differences for Learner Modeling in Intelligent Tutors from Previous Learner Activities 从以往的学习者活动预测智能导师对学习者建模的个体差异

Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization Pub Date : 2016-07-13 DOI: 10.1145/2930238.2930255

Michael Eagle, Albert T. Corbett, John C. Stamper, B. McLaren, R. Baker, Angela Z. Wagner, Benjamin A. MacLaren, Aaron P. Mitchell

{"title":"Predicting Individual Differences for Learner Modeling in Intelligent Tutors from Previous Learner Activities","authors":"Michael Eagle, Albert T. Corbett, John C. Stamper, B. McLaren, R. Baker, Angela Z. Wagner, Benjamin A. MacLaren, Aaron P. Mitchell","doi":"10.1145/2930238.2930255","DOIUrl":"https://doi.org/10.1145/2930238.2930255","url":null,"abstract":"This study examines how accurately individual student differences in learning can be predicted from prior student learning activities. Bayesian Knowledge Tracing (BKT) predicts learner performance well and has often been employed to implement cognitive mastery. Standard BKT individualizes parameter estimates for knowledge components, but not for learners. Studies have shown that individualizing parameters for learners improves the quality of BKT fits and can lead to very different (and potentially better) practice recommendations. These studies typically derive best-fitting individualized learner parameters from learner performance in existing data logs, making the methods difficult to deploy in actual tutor use. In this work, we examine how well BKT parameters in a tutor lesson can be individualized based on learners' prior performance in reading instructional text, taking a pretest, and completing an earlier tutor lesson. We find that best-fitting individual difference estimates do not directly transfer well from one tutor lesson to another, but that predictive models incorporating variables extracted from prior reading, pretest and tutor activities perform well, when compared to a standard BKT model and a model with best-fitting individualized parameter estimates.","PeriodicalId":339100,"journal":{"name":"Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131308448","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}

引用次数: 12

Tag-Enhanced Collaborative Filtering for Increasing Transparency and Interactive Control 标签增强协同过滤，提高透明度和交互式控制

Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization Pub Date : 2016-07-13 DOI: 10.1145/2930238.2930287

Tim Donkers, Benedikt Loepp, J. Ziegler

引用次数: 14

Adaptive Exercise Selection for an Intelligent Tutoring System 智能辅导系统的适应性运动选择

Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization Pub Date : 2016-07-13 DOI: 10.1145/2930238.2930369

J. Okpo

引用次数: 5

Recommendations with Optimal Combination of Feature-Based and Item-Based Preferences 基于功能和基于项目的偏好的最佳组合的推荐

Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization Pub Date : 2016-07-13 DOI: 10.1145/2930238.2930282

M. Nasery, Matthias Braunhofer, F. Ricci

引用次数: 12