The ability to provide high quality personalized recommendations is among the most significant types of competitive advantage an online business can have. However, even having vast amounts of data, creating a recommender system is far from being trivial. This tutorial covers applying deep learning models for creating robust item and user representations for personalized recommender systems, as well as some of the typical problems encountered when working on production recommender systems and possible solutions for these problems.
{"title":"Practical Representation Learning for Recommender Systems","authors":"O. Zakharchuk","doi":"10.1145/3176349.3176900","DOIUrl":"https://doi.org/10.1145/3176349.3176900","url":null,"abstract":"The ability to provide high quality personalized recommendations is among the most significant types of competitive advantage an online business can have. However, even having vast amounts of data, creating a recommender system is far from being trivial. This tutorial covers applying deep learning models for creating robust item and user representations for personalized recommender systems, as well as some of the typical problems encountered when working on production recommender systems and possible solutions for these problems.","PeriodicalId":198379,"journal":{"name":"Proceedings of the 2018 Conference on Human Information Interaction & Retrieval","volume":"220 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120838938","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 aim of this study is to identify social effects on task-based information seeking behavior. Task has been studied for understanding information seeking behavior in relation to task properties and task performers» characteristics. However, there has been little attention to social contexts of task. This work focuses on social aspects of task performance and information seeking behavior by analyzing effects of a social context in which task is generated and conducted on cognition of individual performers. A novel theoretical framework has been designed based on literature on information science and sociology. In the future, data will be collected using self-recorded diaries and subsequent in-depth interviews.
{"title":"Exploring the Effects of Social Contexts on Task-Based Information Seeking Behavior","authors":"Eun Youp Rha","doi":"10.1145/3176349.3176356","DOIUrl":"https://doi.org/10.1145/3176349.3176356","url":null,"abstract":"The aim of this study is to identify social effects on task-based information seeking behavior. Task has been studied for understanding information seeking behavior in relation to task properties and task performers» characteristics. However, there has been little attention to social contexts of task. This work focuses on social aspects of task performance and information seeking behavior by analyzing effects of a social context in which task is generated and conducted on cognition of individual performers. A novel theoretical framework has been designed based on literature on information science and sociology. In the future, data will be collected using self-recorded diaries and subsequent in-depth interviews.","PeriodicalId":198379,"journal":{"name":"Proceedings of the 2018 Conference on Human Information Interaction & Retrieval","volume":"208 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121454008","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}
Memory augmentation is the process of providing human memory with information that facilitates and complements the recall of an event in a person»s past. Recently, there has been a lot of attention on processing the content of meetings for later reuse, such as reviewing a meeting for supporting failing memories, keeping in mind key issues, verification, etc. That is due to the fact that meetings are essential for sharing knowledge in organizations. In this paper, we propose four novel time-series methods for predicting the topics that one should review in preparation for a next meeting. The predicted/recommended topics can be reviewed by a user as a memory augmentation process to facilitate recall of key points of a previous meeting. With the growing number of meetings at an organization that one may attend weekly and with the growing number of topics discussed, forgetting past meetings becomes eminent, hence recommending certain topics to the user in order to prepare the user for a future meeting is beneficial and important. Our experimental results on real-world data, demonstrate that our methods significantly outperform a state-of-the-art Hidden Markov Model baseline. This indicates the efficacy of our proposed methods for modeling semantics in temporal data.
{"title":"Augmentation of Human Memory: Anticipating Topics that Continue in the Next Meeting","authors":"Seyed Ali Bahrainian, F. Crestani","doi":"10.1145/3176349.3176399","DOIUrl":"https://doi.org/10.1145/3176349.3176399","url":null,"abstract":"Memory augmentation is the process of providing human memory with information that facilitates and complements the recall of an event in a person»s past. Recently, there has been a lot of attention on processing the content of meetings for later reuse, such as reviewing a meeting for supporting failing memories, keeping in mind key issues, verification, etc. That is due to the fact that meetings are essential for sharing knowledge in organizations. In this paper, we propose four novel time-series methods for predicting the topics that one should review in preparation for a next meeting. The predicted/recommended topics can be reviewed by a user as a memory augmentation process to facilitate recall of key points of a previous meeting. With the growing number of meetings at an organization that one may attend weekly and with the growing number of topics discussed, forgetting past meetings becomes eminent, hence recommending certain topics to the user in order to prepare the user for a future meeting is beneficial and important. Our experimental results on real-world data, demonstrate that our methods significantly outperform a state-of-the-art Hidden Markov Model baseline. This indicates the efficacy of our proposed methods for modeling semantics in temporal data.","PeriodicalId":198379,"journal":{"name":"Proceedings of the 2018 Conference on Human Information Interaction & Retrieval","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128284625","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}
Why do we listen to music? This question has as many answers as there are people, which may vary by time of day, and the activity of the listener. We envision a contextual music search and recommendation system, which could suggest appropriate music to the user in the current context. As an important step in this direction, we set out to understand what are the users» intents for listening to music, and how they relate to common daily activities. To accomplish this, we conduct and analyze a survey of why and when people of different ages and in different countries listen to music. The resulting categories of common musical intents, and the associations of intents and activities, could be helpful for guiding the development and evaluation of contextual music recommendation systems.
{"title":"Understanding Music Listening Intents During Daily Activities with Implications for Contextual Music Recommendation","authors":"Sergey Volokhin, Eugene Agichtein","doi":"10.1145/3176349.3176885","DOIUrl":"https://doi.org/10.1145/3176349.3176885","url":null,"abstract":"Why do we listen to music? This question has as many answers as there are people, which may vary by time of day, and the activity of the listener. We envision a contextual music search and recommendation system, which could suggest appropriate music to the user in the current context. As an important step in this direction, we set out to understand what are the users» intents for listening to music, and how they relate to common daily activities. To accomplish this, we conduct and analyze a survey of why and when people of different ages and in different countries listen to music. The resulting categories of common musical intents, and the associations of intents and activities, could be helpful for guiding the development and evaluation of contextual music recommendation systems.","PeriodicalId":198379,"journal":{"name":"Proceedings of the 2018 Conference on Human Information Interaction & Retrieval","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128042583","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}
Having become integral to daily life, smartphones become a main tool in addressing daily information needs. Smartphones provide immediate and ubiquitous access to the internet. Mobile apps are becoming popular resources for the general public and patients to obtain health-related information and to self-manage their health. Little is known about patients' needs for information in the context of their phone use. Thus, this study investigates the context of emergence of information needs of diabetes patients using smartphones. This study focuses on the chronic disease type 2 diabetes because patients with this condition are required to take an active role in managing their condition on a daily basis. This study employs employ a web-based survey using the critical incident technique. This study has theoretical significance and practical implications. Information needs should be conceptualized in the contexts that give rise to them. This study will enrich our understanding of multi-faceted information needs related to chronic disease self-care in daily life. Understanding the information needs of diabetes patients and the contexts for the needs is necessary to help researchers and designers develop mobile services to satisfy patients' needs and requirements.
{"title":"Contextualizing Information Needs of Patients with Chronic Conditions Using Smartphones","authors":"Henna Kim","doi":"10.1145/3176349.3176352","DOIUrl":"https://doi.org/10.1145/3176349.3176352","url":null,"abstract":"Having become integral to daily life, smartphones become a main tool in addressing daily information needs. Smartphones provide immediate and ubiquitous access to the internet. Mobile apps are becoming popular resources for the general public and patients to obtain health-related information and to self-manage their health. Little is known about patients' needs for information in the context of their phone use. Thus, this study investigates the context of emergence of information needs of diabetes patients using smartphones. This study focuses on the chronic disease type 2 diabetes because patients with this condition are required to take an active role in managing their condition on a daily basis. This study employs employ a web-based survey using the critical incident technique. This study has theoretical significance and practical implications. Information needs should be conceptualized in the contexts that give rise to them. This study will enrich our understanding of multi-faceted information needs related to chronic disease self-care in daily life. Understanding the information needs of diabetes patients and the contexts for the needs is necessary to help researchers and designers develop mobile services to satisfy patients' needs and requirements.","PeriodicalId":198379,"journal":{"name":"Proceedings of the 2018 Conference on Human Information Interaction & Retrieval","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132508623","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 explore the gap between 1) statistically significant relationships between task and browsing behavior and 2) predicting task type from such behaviors. Previous literature has shown relationships between Web browsing behavior and person»s corresponding search task. We find statistically significant browser features for detecting task - comparing the features to previous literature - and apply this knowledge to task classification of search sessions. Even though significant features improve prediction over baselines, it is not by much. We suggest that a more subtle treatment of such features should go beyond statistical significance. In some cases, considering personal patterns may be required for effective prediction.
{"title":"The Paradox of Personalization: Does Task Prediction Require Individualized Models?","authors":"M. Mitsui, Jiqun Liu, C. Shah","doi":"10.1145/3176349.3176887","DOIUrl":"https://doi.org/10.1145/3176349.3176887","url":null,"abstract":"We explore the gap between 1) statistically significant relationships between task and browsing behavior and 2) predicting task type from such behaviors. Previous literature has shown relationships between Web browsing behavior and person»s corresponding search task. We find statistically significant browser features for detecting task - comparing the features to previous literature - and apply this knowledge to task classification of search sessions. Even though significant features improve prediction over baselines, it is not by much. We suggest that a more subtle treatment of such features should go beyond statistical significance. In some cases, considering personal patterns may be required for effective prediction.","PeriodicalId":198379,"journal":{"name":"Proceedings of the 2018 Conference on Human Information Interaction & Retrieval","volume":"140 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122947658","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 conversational nature of intelligent personal assistants (IPAs) has the potential to trigger personification tendencies in users, which in turn can translate into consumer loyalty and satisfaction. We conducted a study of Amazon Alexa usage and explored the manifestations and possible correlates of users' personification of Alexa. The data were collected via diary instrument from nineteen Alexa users over four days. Less than half of the participants reported personification behaviors. Most of the personification reports can be characterized as mindless politeness (saying 'thank you' and 'please' to Alexa). Two participants expressed deeper personification by confessing their love and reprimanding Alexa. A new study is underway to understand whether expressions of personifications are caused by users' emotional attachments or skepticism about technology's intelligence.
{"title":"Personification of the Amazon Alexa: BFF or a Mindless Companion","authors":"Irene Lopatovska, Harriet Williams","doi":"10.1145/3176349.3176868","DOIUrl":"https://doi.org/10.1145/3176349.3176868","url":null,"abstract":"The conversational nature of intelligent personal assistants (IPAs) has the potential to trigger personification tendencies in users, which in turn can translate into consumer loyalty and satisfaction. We conducted a study of Amazon Alexa usage and explored the manifestations and possible correlates of users' personification of Alexa. The data were collected via diary instrument from nineteen Alexa users over four days. Less than half of the participants reported personification behaviors. Most of the personification reports can be characterized as mindless politeness (saying 'thank you' and 'please' to Alexa). Two participants expressed deeper personification by confessing their love and reprimanding Alexa. A new study is underway to understand whether expressions of personifications are caused by users' emotional attachments or skepticism about technology's intelligence.","PeriodicalId":198379,"journal":{"name":"Proceedings of the 2018 Conference on Human Information Interaction & Retrieval","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123197508","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}
Soon-Gyo Jung, Joni O. Salminen, Haewoon Kwak, Jisun An, B. Jansen
We present Automatic Persona Generation (APG), a methodology and system for quantitative persona generation using large amounts of online social media data. The system is operational, beta deployed with several client organizations in multiple industry verticals and ranging from small-to-medium sized enterprises to large multi-national corporations. Using a robust web framework and stable back-end database, APG is currently processing tens of millions of user interactions with thousands of online digital products on multiple social media platforms, such as Facebook and YouTube. APG identifies both distinct and impactful user segments and then creates persona descriptions by automatically adding pertinent features, such as names, photos, and personal attributes. We present the overall methodological approach, architecture development, and main system features. APG has a potential value for organizations distributing content via online platforms and is unique in its approach to persona generation. APG can be found online at https://persona.qcri.org.
{"title":"Automatic Persona Generation (APG): A Rationale and Demonstration","authors":"Soon-Gyo Jung, Joni O. Salminen, Haewoon Kwak, Jisun An, B. Jansen","doi":"10.1145/3176349.3176893","DOIUrl":"https://doi.org/10.1145/3176349.3176893","url":null,"abstract":"We present Automatic Persona Generation (APG), a methodology and system for quantitative persona generation using large amounts of online social media data. The system is operational, beta deployed with several client organizations in multiple industry verticals and ranging from small-to-medium sized enterprises to large multi-national corporations. Using a robust web framework and stable back-end database, APG is currently processing tens of millions of user interactions with thousands of online digital products on multiple social media platforms, such as Facebook and YouTube. APG identifies both distinct and impactful user segments and then creates persona descriptions by automatically adding pertinent features, such as names, photos, and personal attributes. We present the overall methodological approach, architecture development, and main system features. APG has a potential value for organizations distributing content via online platforms and is unique in its approach to persona generation. APG can be found online at https://persona.qcri.org.","PeriodicalId":198379,"journal":{"name":"Proceedings of the 2018 Conference on Human Information Interaction & Retrieval","volume":"450 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125805077","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}
As search tasks move beyond targeted search and into the domain of complex search, a substantial cognitive burden is placed on the searcher to craft and refine their queries, evaluate and explore among the search results, and ultimately make use of what is found. In such cases, information visualization techniques may be leveraged to enable searchers to perceive, interpret, and make sense of the information available throughout the search process. This tutorial will establish the fundamental principles and theories of information visualization, explain how information visualization can support interactive information retrieval, and survey search interfaces from my own research that leverage information visualization techniques. The goal of this tutorial will be to encourage researchers to make informed design decisions for how to integrate information visualization into their own interactive information retrieval projects.
{"title":"Information Visualization for Interactive Information Retrieval","authors":"O. Hoeber","doi":"10.1145/3176349.3176898","DOIUrl":"https://doi.org/10.1145/3176349.3176898","url":null,"abstract":"As search tasks move beyond targeted search and into the domain of complex search, a substantial cognitive burden is placed on the searcher to craft and refine their queries, evaluate and explore among the search results, and ultimately make use of what is found. In such cases, information visualization techniques may be leveraged to enable searchers to perceive, interpret, and make sense of the information available throughout the search process. This tutorial will establish the fundamental principles and theories of information visualization, explain how information visualization can support interactive information retrieval, and survey search interfaces from my own research that leverage information visualization techniques. The goal of this tutorial will be to encourage researchers to make informed design decisions for how to integrate information visualization into their own interactive information retrieval projects.","PeriodicalId":198379,"journal":{"name":"Proceedings of the 2018 Conference on Human Information Interaction & Retrieval","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127337546","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 propose query priming to activate careful user information seeking in web searches. Query priming employs query auto-completion (QAC) and query suggestion (QS) to present search terms that stimulate critical thinking and encourages careful information seeking and decision making. We conducted an online user study using a crowdsourcing service. Analysis of search behavior logs and questionnaire responses confirmed the following. (1) With query priming, participants issued more queries and (re-)visited search engine result pages more frequently. (2) Query priming promoted webpage selection targeted at evidence-based decision making. (3) The query priming effect varied relative to participant educational background. This study contributes to search interaction design to enhance user engagement in critical thinking in web searches.
{"title":"Query Priming for Promoting Critical Thinking in Web Search","authors":"Yusuke Yamamoto, Takehiro Yamamoto","doi":"10.1145/3176349.3176377","DOIUrl":"https://doi.org/10.1145/3176349.3176377","url":null,"abstract":"We propose query priming to activate careful user information seeking in web searches. Query priming employs query auto-completion (QAC) and query suggestion (QS) to present search terms that stimulate critical thinking and encourages careful information seeking and decision making. We conducted an online user study using a crowdsourcing service. Analysis of search behavior logs and questionnaire responses confirmed the following. (1) With query priming, participants issued more queries and (re-)visited search engine result pages more frequently. (2) Query priming promoted webpage selection targeted at evidence-based decision making. (3) The query priming effect varied relative to participant educational background. This study contributes to search interaction design to enhance user engagement in critical thinking in web searches.","PeriodicalId":198379,"journal":{"name":"Proceedings of the 2018 Conference on Human Information Interaction & Retrieval","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126461930","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：