User Modeling.md

User Understanding for Recommender System

The recommendation system, relying on historical observational data to model the complex relationships among users and items, has achieved great success in real-world applications.

But those static profiles don’t (fully) reflect users’ personalized preferences. In addition, most existing preference learning methods are based on users’ matching behaviors. However, matching behaviors are sparse due to the nature of PJF and not fine-grained enough to reflect users’ dynamic preferences.

• https://mdds.net.technion.ac.il/files/2019/03/CAMC-KT.pdf
• Second Uber Science Symposium: Exploring Advances in Behavioral Science
• First Uber Science Symposium: Discussing the Next Generation of RL, NLP, ConvAI, and DL

User Modeling

User models are used to generate or adapt user interfaces at runtime, to address particular user needs and preferences. User models are also known as user profiles, personas or archetypes. They can be used by designers and developers for personalization purposes and to increase the usability and accessibility of products and services.

• https://www.um.org/
• https://www.um.org/umap2020/
• https://www.um.org/awards/best-paper-awards
• https://www.w3.org/WAI/RD/wiki/User_modeling
• https://www2018.thewebconf.org/program/user-modeling/
• http://kdd2018tutorial-behavior.datasciences.org/
• https://www2019.thewebconf.org/research-track/user-modeling-personalization-and-experience
• User Modeling: Recent Work, Prospects and Hazards1
• Research on the Use, Characteristics, and Impact of e-Commerce Product Recommendation Agents: A Review and Update for 2007–2012
• Beyond Bags of Words: Modeling Implicit User Preferences in Information Retrieval
• Modeling User Exposure in Recommendation
• E-Commerce Product Recommendation Agents: Use, Characteristics, and Impact
• Modeling User Preferences and Mediating Agents in Electronic Commerce
• http://www.humanize-workshop.org/
• http://iwum.org/

Modeling Users’ Preferences

The ever-growing nature of user generated data in online systems poses obvious challenges on how we process such data. Typically, this issue is regarded as a scalability problem and has been mainly addressed with distributed algorithms able to train on massive amounts of data in short time windows. However, data is inevitably adding up at high speeds. Eventually one needs to discard or archive some of it. Moreover, the dynamic nature of data in user modeling and recommender systems, such as change of user preferences, and the continuous introduction of new users and items make it increasingly difficult to maintain up-to-date, accurate recommendation models.

• Workshop on Online Recommender Systems and User Modeling
• Modeling Users’ Preferences and Social Links in Social Networking Services: A Joint-Evolving Perspective
• Modeling and Learning User Preferences Over Sets
• Modeling the Dynamics of User Preferences in Coupled Tensor Factorization
• Adaptive User Modeling with Long and Short-Term Preferences for Personalized Recommendation
• Temporal Modeling of User Preferences in Recommender System
• Modeling Sequential Preferences with Dynamic User and Context Factors
• Deep Modeling of the Evolution of User Preferences and Item Attributes in Dynamic Social Networks
• Modeling Users’ Mobile App Privacy Preferences: Restoring Usability in a Sea of Permission Settings

User Engagement

User engagement measures whether users find value in a product or service. Engagement can be measured by a variety or combination of activities such as downloads, clicks, shares, and more. Highly engaged users are generally more profitable, provided that their activities are tied to valuable outcomes such as purchases, signups, subscriptions, or clicks.

• WHAT IS USER ENGAGEMENT?
• What is Customer Engagement, and Why is it Important?
• What is user engagement? A conceptual framework for defining user engagement with technology
• How to apply AI for customer engagement
• The future of customer engagement
• Measuring User Engagement
• https://inlabdigital.com/
• https://www.futurelab.net/
• http://www.ueo-workshop.com/

• The User Engagement Optimization Workshop2
• The User Engagement Optimization Workshop1
• EVALUATION OF USER EXPERIENCE IN MOBILE ADVERTISING
• WWW 2019 Tutorial on Online User Engagement
• http://www.ueo-workshop.com/
• https://www.nngroup.com/
• https://labtomarket.eu/
• http://research.google.com/pubs/AmrAhmed.html
• https://home.ubalt.edu/ntsbarsh/business-stat/opre504.htm
• https://www.nersc.gov/about/nersc-staff/user-engagement/
• https://www.microsoft.com/en-us/research/people/eladyt/
• http://yom-tov.info/

Click Modeling

Click models are mathematical models that attempt to do just that: Describe a typical userʼs decision process as he or she interacts with the search results page, so that we may infer said userʼs judgments on the relevance and irrelevance of specific search results.