Report on the WSDM 2020 workshop on state-based user modelling (SUM'20) (original) (raw)

SIGIR 2009 workshop on understanding the user

ACM SIGIR Forum, 2009

Modern information search systems can benefit greatly from using additional information about the user and the user's behavior, and research in this area is active and growing. Feedback data based on direct interaction (e.g., clicks, scrolling, etc.) as well as on user profiles/preferences has been proven valuable for personalizing the search process, e.g., from how queries are understood to how relevance is assessed. New technology has made it inexpensive and easy to collect more feedback data and more different types of data (e.g., gaze, emotional, or biometric data).

A System for Context-Dependent User Modeling

2006

We present a system for learning and utilizing context-dependent user models. The user models attempt to capture the interests of a user and link the interests to the situation of the user. The models are used for making recommendations to applications and services on what might interest the user in her current situation. In the design process we have analyzed several mock-ups of new mobile, context-aware services and applications. The mock-ups spanned rather diverse domains, which helped us to ensure that the system is applicable to a wide range of tasks, such as modality recommendations (e.g., switching to speech output when driving a car), service category recommendations (e.g., journey planners at a bus stop), and recommendations of group members (e.g., people with whom to share a car). The structure of the presented system is highly modular. First of all, this ensures that the algorithms that are used to build the user models can be easily replaced. Secondly, the modularity makes it easier to evaluate how well different algorithms perform in different domains. The current implementation of the system supports rule based reasoning and tree augmented naïve Bayesian classifiers (TAN). The system consists of three components, each of which has been implemented as a web service. The entire system has been deployed and is in use in the EU IST project MobiLife. In this paper, we detail the components that are part of the system and introduce the interactions between the components. In addition, we briefly discuss the quality of the recommendations that our system produces.

User modeling: Recent work, prospects and hazards

1993

Abstract User modeling has made considerable progress during its existence now of more than a decade. In this paper, a survey of recent developments will be presented, which concentrates on the modeling of a user's knowledge, plans, and preferences in a domain, on the exploitation of new sources of information about the user, on issues of representation, inference and revision, on user modeling shell systems and servers, and on the verification of the practical utility of user models.

Hybrid User Model for Capturing a User’s Information Seeking Intent

Smart Innovation, Systems and Technologies, 2013

Modeling a user and their knowledge is a critical issue in successfully determining and evaluating collective intelligence. In this chapter, we study the problem of employing a cognitive user model for information retrieval in which knowledge about a user is captured and used for improving his/her performance in an information seeking task. This problem is very important to group intelligence analysis involving elements such as collaborative information retrieval and social information retrieval because knowledge about each individual needs to be used in order to improve a group's effectiveness in information seeking. Our solution is to improve the effectiveness of a user in a search by developing a hybrid user model to capture user intent dynamically and combines the captured intent with an awareness of the components of an information retrieval system. The term "hybrid" refers to the methodology of combining the understanding of a user with the insights into a system all unified within a decision theoretic framework. In this model, multi-attribute utility theory is used to evaluate values of the attributes describing a user's intent in combination with the attributes describing an information retrieval system. We use the existing research on predicting query performance and on determining dissemination thresholds to create functions to evaluate these selected attributes. This approach also offers fine-grained representation of the model and the ability to learn a user's knowledge dynamically. We compare this approach with the best traditional approach for relevance feedback in the information retrieval community -Ide dec-hi, using term frequency inverted document frequency (TFIDF) weighting on selected collections from the information retrieval community such as CRANFIELD, MEDLINE, and CACM. The evaluations with our hybrid model with these testbeds shows that this approach retrieves more relevant documents in the first 15 returned documents than the TFIDF approach for all three collections, as well as more relevant documents on MEDLINE and CRANFIELD in both initial and feedback runs, while being competitive with the Ide dec-hi approach in the feedback runs for the CACM collection. We also demonstrate the use of our user model to dynamically create a common knowledge base from the users' queries and relevant snippets using the APEX 07 data set.

A Survey of User Profiling: State-of-the-Art, Challenges, and Solutions

IEEE Access, 2019

Advancements in information and communication technology, and online web users have given attention to the virtual representation of each user, which is crucial for effective service personalization. Meeting users need and preferences is an ongoing challenge in service personalization. This issue can be addressed through the building of a comprehensive user profile. A user profile is the summary of the user's interests, characteristics, behaviours, and preferences, while user profiling is the system of collecting, organizing and inferring the user profile information. Many reviews on user profiling have been conducted but none focused on the effective profile modeling process. Hence, this article aims to provide a review of the recent state-of-the-art approach to user profiling. These include methods, description, characteristics, and taxonomy of the user profile. The study of the existing user profiling modeling in the aspect of data acquisition, feature extraction, profiling techniques, and profiling approaches (with the identification of their strengths and weaknesses) and the performance measures are also provided. In addition, the research challenges were also discussed with a focus on privacy, datasets, cold start issues, trust issues, and computational complexity. Moreover, the article identified an open research direction that serves as solutions to the identified challenges and motivation for further researchers in advancing user profiling. The findings showed that an effective modeling process enhances the construction of accurate user profile for service personalization.

iv Non-Invasive User Modelling to Support

2010

While user modelling and personalisation is an ongoing area of research, it is also a mature field with work dating back more than twenty five years with no system having gained mass adoption. In this work we introduce AMS, a user modelling system that works silently in the background while users browse the internet, modelling browsing behaviour, collecting browsing data and analysing it with a view to inferring the user's interests. Prevalent issues from similar systems, such as privacy concerns or intrusion to the user's browsing experience are nicely circumvented here as we engineer the data to being contained and stored at the user's browser while only using implicit methods to collect the data. Text analytics are used to extract key terms from the raw data which is collected from pages that the user visits and a rating is applied to these terms, taking into consideration the time spent actively viewing the page with respect to the length of the page. We show how AMS is effective in surmising the user's interests, within the bounds of the evaluations that were carried out and we show how getting results from the linked data environment played a role in enhancing the user's overall experience. v This work is dedicated with love to my mother Annie and my mother-in-law Lily Contents Acknowledgments iv List of Tables x List of Figures xi Chapter 1 Introduction

Predictive statistical models for user modeling

User Modeling and User-Adapted Interaction, 2001

The limitations of traditional knowledge representation methods for modeling complex human behaviour led to the investigation of statistical models. Predictive statistical models enable the anticipation of certain aspects of human behaviour, such as goals, actions and preferences. In this paper, we motivate the development of these models in the context of the user modeling enterprise.We then review the two main approaches to predictive statistical modeling, content-based and collaborative, and discuss the main techniques used to develop predictive statistical models. We also consider the evaluation requirements of these models in the user modeling context, and propose topics for future research.