2019 IEEE/WIC/ACM International Conference on Web Intelligence (WI)最新文献_第7页

End-to-end Personalization of Digital Health Interventions using Raw Sensor Data with Deep Reinforcement Learning : A comparative study in digital health interventions for behavior change 使用原始传感器数据和深度强化学习的数字健康干预的端到端个性化:行为改变的数字健康干预的比较研究

2019 IEEE/WIC/ACM International Conference on Web Intelligence (WI) Pub Date : 2019-10-01 DOI: 10.1145/3350546.3352527

Ali el Hassouni, M. Hoogendoorn, A. Eiben, M. V. Otterlo, Vesa Muhonen

{"title":"End-to-end Personalization of Digital Health Interventions using Raw Sensor Data with Deep Reinforcement Learning : A comparative study in digital health interventions for behavior change","authors":"Ali el Hassouni, M. Hoogendoorn, A. Eiben, M. V. Otterlo, Vesa Muhonen","doi":"10.1145/3350546.3352527","DOIUrl":"https://doi.org/10.1145/3350546.3352527","url":null,"abstract":"We introduce an end-to-end reinforcement learning (RL) solution for the problem of sending personalized digital health interventions. Previous work has shown that personalized interventions can be obtained through RL using simple, discrete state information such as the recent activity performed. In reality however, such features are often not observed, but instead could be inferred from noisy, low-level sensor information obtained from mobile devices (e.g. accelerometers in mobile phones). One could first transform such raw data into discrete activities, but that could throw away important details and would require training a classifier to infer these discrete activities which would need a labeled training set. Instead, we propose to directly learn intervention strategies for the low-level sensor data end-to-end using deep neural networks and RL. We test our novel approach in a self-developed simulation environment which models, and generates, realistic sensor data for daily human activities and show the short-and long-term efficacy of sending personalized physical workout interventions using RL policies. We compare several different input representations and show that learning using raw sensor data is nearly as effective and much more flexible. CCS CONCEPTS • Computing methodologies → Reinforcement learning; Sequential decision making; Online learning settings;","PeriodicalId":171168,"journal":{"name":"2019 IEEE/WIC/ACM International Conference on Web Intelligence (WI)","volume":"97 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125980495","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: 6

Predicting Outcomes of Active Sessions Using Multi-action Motifs 使用多动作主题预测活动会话的结果

2019 IEEE/WIC/ACM International Conference on Web Intelligence (WI) Pub Date : 2019-10-01 DOI: 10.1145/3350546.3352495

Weiqiang Lin, Natasa Milic-Frayling, K. Zhou, Eugene Ch’ng

{"title":"Predicting Outcomes of Active Sessions Using Multi-action Motifs","authors":"Weiqiang Lin, Natasa Milic-Frayling, K. Zhou, Eugene Ch’ng","doi":"10.1145/3350546.3352495","DOIUrl":"https://doi.org/10.1145/3350546.3352495","url":null,"abstract":"Web sites and online services increasingly engage with users through live chats to provide support, advice, and offers. Such approaches require reliable methods to predict the user’s intent and make an informed decision when and how to intervene during an active session. Prior work on predicting purchase intent involved click-stream data mining and feature construction in an ad-hoc manner with a moderate success (AUC 0.70 range). We demonstrate the use of the consumer Purchase Decision Model (PDM) and a principled way of constructing features predictive of the purchase intent. We show that the Logistic Regression (LR) classifiers, trained with multi-action motifs, perform on par with the state-of-the-art LSTM sequence model achieving comparable AUC (0.95 vs 0.96) and performing better for the sparse purchase sessions, with higher recall (0.85 vs 0.61) and higher F1 score (0.73 vs 0.66). While LSTM performs better than LR in terms of weighted averages of F1, precision, and recall, it requires 7 times longer to train and offers no insights about the predictive model in terms of the user actions and the purchase decision stages. The LR predictors are robust and effective in simulating real-time interventions, achieving F1 of 0.84 and AUC of 0.85 after observing only 50% of an active session. For non-purchase sessions that leaves room for live intervention, on average within 8 actions before the session ends. CCS CONCEPTS • Information system → Misc.","PeriodicalId":171168,"journal":{"name":"2019 IEEE/WIC/ACM International Conference on Web Intelligence (WI)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121851782","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: 3

Towards Issue Recommendation for Open Source Communities 面向开源社区的问题建议

2019 IEEE/WIC/ACM International Conference on Web Intelligence (WI) Pub Date : 2019-10-01 DOI: 10.1145/3350546.3352514

Ralph Samer, A. Felfernig, Martin Stettinger

{"title":"Towards Issue Recommendation for Open Source Communities","authors":"Ralph Samer, A. Felfernig, Martin Stettinger","doi":"10.1145/3350546.3352514","DOIUrl":"https://doi.org/10.1145/3350546.3352514","url":null,"abstract":"In open source software development, a major challenge is the prioritization of new requirements as well as the identification of responsible developers for their implementation. Unlike conventional industrial software development, where requirements engineers have to explicitly define who implements what, in the context of open source development, developers (contributors) usually decide on their own which requirements to implement next. Contributors have to deal with a huge number of requirements where the recognition of the most relevant ones often becomes a crucial task with a high impact on the success of a software project. This fact defines our major motivation for the development of a prioritization tool for the ECLIPSE community which recommends relevant requirements (issues/bugs) to open source developers. Our tool uses real-world data from ECLIPSE in order to build a prediction model. We trained and tested our tool with different classifiers such as Naive Bayes (representing our baseline), Decision Tree, and Random Forest. The evaluation results indicate that the Random Forest classifier correctly predicts issues with a precision of 0.88 (F1-score 0.68).CCS CONCEPTS• Information systems → Recommender systems; • Humancentered computing → Open source software; • Computing methodologies → Machine learning approaches; Natural language processing; • Software and its engineering → Requirements analysis.","PeriodicalId":171168,"journal":{"name":"2019 IEEE/WIC/ACM International Conference on Web Intelligence (WI)","volume":"24 9","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114006605","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: 3

What is Real or Fake?-Machine Learning Approaches for Rumor Verification using Stance CIassification 什么是真假?-基于姿态分类的谣言验证机器学习方法

2019 IEEE/WIC/ACM International Conference on Web Intelligence (WI) Pub Date : 2019-10-01 DOI: 10.1145/3350546.3352562

Paulo Roberto da Cordeiro, V. Pinheiro, Ronaldo S. Moreira, Cecilia Carvalho, Livio Freire

引用次数: 6

Disjunctive Sets of Phrase Queries for Diverse Query Suggestion 基于不同查询建议的短语查询析取集

2019 IEEE/WIC/ACM International Conference on Web Intelligence (WI) Pub Date : 2019-10-01 DOI: 10.1145/3350546.3352566

Ziyang Liao, Keishi Tajima

引用次数: 1

Predicting Future Participants of Information Propagation Trees 预测信息传播树的未来参与者

2019 IEEE/WIC/ACM International Conference on Web Intelligence (WI) Pub Date : 2019-10-01 DOI: 10.1145/3350546.3352540

Hsing-Huan Chung, Hen-Hsen Huang, Hsin-Hsi Chen

引用次数: 2

Not a Target. A Deep Learning Approach for a Warning and Decision Support System to Improve Safety and Security of Humanitarian Aid Workers 不是目标。基于深度学习的预警和决策支持系统提高人道主义援助工作者的安全保障

2019 IEEE/WIC/ACM International Conference on Web Intelligence (WI) Pub Date : 2019-10-01 DOI: 10.1145/3350546.3352551

M. B. Lazreg, N. Noori, T. Comes, M. G. Olsen

{"title":"Not a Target. A Deep Learning Approach for a Warning and Decision Support System to Improve Safety and Security of Humanitarian Aid Workers","authors":"M. B. Lazreg, N. Noori, T. Comes, M. G. Olsen","doi":"10.1145/3350546.3352551","DOIUrl":"https://doi.org/10.1145/3350546.3352551","url":null,"abstract":"Humanitarian aid workers who try to provide aid to the most vulnerable populations in the Middle East or Africa are risking their own lives and safety to help others. The current lack of a collaborative real-time information system to predict threats prevents responders and local partners from developing a shared understanding of potentially threatening situations, causing increased response times and leading to inadequate protection. To solve this problem, this paper presents a threat detection and decision support system that combines knowledge and information from a network of responders with automated and modular threat detection. The system consists of three parts. It first collects textual information, ranging from social media, and online news reports to reports and text messages from a decentralized network of humanitarian staff. Second, the system uses deep neural network techniques to automatically detects a threat or incident and provide information including location, threat category, and casualties. Third, given the type of threat and the information extracted by the NER, a feedforward network proposes a mitigation plan based on humanitarian standard operating procedures. The classified information is rapidly redistributed to potentially affected humanitarian workers at any level. The system testing results show a high precision of 0.91 and 0.98 as well as an F-measure of 0.87 and 0.88 in detecting the threats and decision support respectively. We thus combine the collaborative intelligence of a decentralized network of aid workers with the power of deep neural networks. CCS CONCEPTS • Computing methodologies → Neural networks.","PeriodicalId":171168,"journal":{"name":"2019 IEEE/WIC/ACM International Conference on Web Intelligence (WI)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121951625","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: 2

Personality Recognition in Conversations using Capsule Neural Networks 会话中使用胶囊神经网络的人格识别

2019 IEEE/WIC/ACM International Conference on Web Intelligence (WI) Pub Date : 2019-10-01 DOI: 10.1145/3350546.3352516

E. A. Ríssola, Seyed Ali Bahrainian, F. Crestani

引用次数: 20

Unintended Bias in Misogyny Detection 厌女症检测中的意外偏见

2019 IEEE/WIC/ACM International Conference on Web Intelligence (WI) Pub Date : 2019-10-01 DOI: 10.1145/3350546.3352512

Debora Nozza, Claudia Volpetti, E. Fersini

{"title":"Unintended Bias in Misogyny Detection","authors":"Debora Nozza, Claudia Volpetti, E. Fersini","doi":"10.1145/3350546.3352512","DOIUrl":"https://doi.org/10.1145/3350546.3352512","url":null,"abstract":"During the last years, the phenomenon of hate against women increased exponentially especially in online environments such as microblogs. Although this alarming phenomenon has triggered many studies both from computational linguistic and machine learning points of view, less effort has been spent to analyze if those misogyny detection models are affected by an unintended bias. This can lead the models to associate unreasonably high misogynous scores to a non-misogynous text only because it contains certain terms, called identity, terms. This work is the first attempt to address the problem of measuring and mitigating unintended bias in machine learning models trained for the misogyny detection task. We propose a novel synthetic test set that can be used as evaluation framework for measuring the unintended bias and different mitigation strategies specific for this task. Moreover, we provide a misogyny detection model that demonstrate to obtain the best classification performance in the state-of-the-art. Experimental results on recently introduced bias metrics confirm the ability of the bias mitigation treatment to reduce the unintended bias of the proposed misogyny detection model. CCS CONCEPTS • Social and professional topics $rightarrow$ Hate speech; • Computing methodologies $rightarrow$ Neural networks.","PeriodicalId":171168,"journal":{"name":"2019 IEEE/WIC/ACM International Conference on Web Intelligence (WI)","volume":"187 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115229930","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: 62

Algorithms and System Architecture for Immediate Personalized News Recommendations 即时个性化新闻推荐的算法和系统架构

2019 IEEE/WIC/ACM International Conference on Web Intelligence (WI) Pub Date : 2019-09-03 DOI: 10.1145/3350546.3352509

T. Yoneda, Shunsuke Kozawa, Keisuke Osone, Yukinori Koide, Yosuke Abe, Yoshifumi Seki

{"title":"Algorithms and System Architecture for Immediate Personalized News Recommendations","authors":"T. Yoneda, Shunsuke Kozawa, Keisuke Osone, Yukinori Koide, Yosuke Abe, Yoshifumi Seki","doi":"10.1145/3350546.3352509","DOIUrl":"https://doi.org/10.1145/3350546.3352509","url":null,"abstract":"Personalization plays an important role in many services, just as news does. Many studies have examined news personalization algorithms, but few have considered practical environments. This paper provides algorithms and system architecture for generating immediate personalized news in a practical environment. Immediacy means changes in news trends and user interests are reflected in recommended news lists quickly. Since news trends and user interests rapidly change, immediacy is critical in news personalization applications. We develop algorithms and system architecture to realize immediacy. Our algorithms are based on collaborative filtering of user clusters and evaluate news articles using click-through rate and decay scores based on the time elapsed since the user’s last access. Existing studies have not fully discussed system architecture, so a major contribution of this paper is that we demonstrate a system architecture and realize our algorithms and a configuration example implemented on top of Amazon Web Services. We evaluate the proposed method both offline and online. The offline experiments are conducted through a real-world dataset from a commercial news delivery service, and online experiments are conducted via A/B testing on production environments. We confirm the effectiveness of our proposed method and also that our system architecture can operate in large-scale production environments.CCS CONCEPTS• Information systems → Personalization; Web service; • Software and its engineering → Real-time systems software.","PeriodicalId":171168,"journal":{"name":"2019 IEEE/WIC/ACM International Conference on Web Intelligence (WI)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126983802","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: 6