Paradigm Shifts in User Modeling: A Journey from Historical Foundations to Emerging Trends

Slide of the tutorial entitled "Paradigm Shifts in User Modeling: A Journey from Historical Foundations to Emerging Trends" held at UMAP'24: 32nd ACM Conference on User Modeling, Adaptation and Personalization (July 1, 2024 | Cagliari, Italy)

1. PARADIGM SHIFTS
IN USER MODELING
A Journey from
Historical Foundations
to Emerging Trends
TUTORIAL
July 1, 2024

2. ABOUT US

3. ABOUT US
Erasmo Purificato
Ph.D. Candidate
Otto von Guericke University Magdeburg, Germany
[email protected]

4. ABOUT US
Ludovico Boratto
Associate Professor
University of Cagliari, Italy
[email protected]

5. ABOUT US
Ernesto William De Luca
Full Professor
Otto von Guericke University Magdeburg, Germany
[email protected]

6. AGENDA

7. HISTORICAL
OVERVIEW
[Purificato et al., 2024, §1.1]

8. “USER MODELING” NOTION INTRODUCED
Pioneering work by Allen, Cohen, Perrault, and Rich
[Perrault et al., 1978; Cohen and Perrault, 1979; Rich, 1979]
set the stage for the research in this field.
In these early models, there is no distinct
separation between the components used for
user modeling and those used for other functions
[Sleeman, 1985; Allgayer et al., 1989; Wahlster and Kobsa, 1989].
1970s
[Purificato et al., 2024, §1.1]

9. NOTION INTRODUCED
Rich
[Perrault et al., 1978; Cohen and Perrault, 1979; Rich, 1979]
set the stage for the research in this field.
In these early models, there is no distinct
separation between the components used for
user modeling and those used for other functions
, 1989].
STEREOTYPE USER MODELING
Constituted the first attempt to differentiate
a user from other users [Rich, 1979]
and inspired several future contributions
[Ardissono and Sestero, 1995; Krulwich, 1997].
1970s
[Purificato et al., 2024, §1.1]

10. GENERIC USER MODELING SYSTEMS
GUMS operate as independent components
within a system during runtime [Finin and Drager, 1986].
Primary GUMS established the foundation for
fundamental systems, such as UMT [Brajnik and Tasso, 1994],
TAGUS [Paiva and Self, 1994], BGP-MS [Kobsa and Pohl, 1994],
Doppelänger [Orwant, 1994], and the Um toolkit [Kay, 1995].
1980s
[Purificato et al., 2024, §1.1]

11. USER MODELING SHELL SYSTEMS
Usually considered equivalent to GUMS,
they are introduced to support complex reasoning
about a user (especially in domains where
characteristics are clearly identified) with
the aim to be broadly adaptable [Kobsa, 1990].,
.
1980s
[Purificato et al., 2024, §1.1]

12. USER MODELING FOR
WEB PERSONALIZATION
The involvement of user modelling is crucial for
the advent of personalization and the transition from
anonymous mass marketing and sales to individualized
one-to-one marketing approaches on the Internet
[Peppers and Rogers, 1993; Caglayan et al., 1997; Konstan et al., 1997;
Fink and Kobsa, 2000; Kay et al., 2002; Brusilovsky, 2004].
1990s
the aim to be broadly adaptable .
[Purificato et al., 2024, §1.1]

13. COMMERCIAL USER MODELING SERVERS
They maintain a user model as a centralized
repository, shared across several applications
through a flexible client-server architecture
[Kobsa, 2001; Kay et al., 2002; Trella et al., 2003; Fink, 2004;
Brusilovsky, 2004; Kobsa and Fink, 2006; Kobsa, 2007].
USER MODELING FOR
WEB PERSONALIZATION
The involvement of user modelling is crucial for
the advent of personalization and the transition from
anonymous mass marketing and sales to individualized
marketing approaches on the Internet
et al., 1997;
.
1990s
[Purificato et al., 2024, §1.1]

14. .
ADAPTIVE HYPERMEDIA
Intersection of hypermedia systems [Kobsa et al., 2001]
and adaptive user interfaces [Langley, 1999].
Adaptive hypermedia [Brusilovsky et al., 1998; Brusilovsky, 2001]
tailored what the user is offered based on a model of
the user’s goals, preferences, and knowledge.
[De Bra et al., 1999; Brusilovsky and Maybury, 2002].
2000s
[Purificato et al., 2024, §1.1]

15. ONTOLOGY-BASED USER MODELING
The advent of the semantic web prompted
investigations into representing and
modeling user preferences through ontologies,
employed to semantically organize
and connect user profiles
[Middleton et al., 2004; Mehta et al., 2005; Sieg et al., 2007;
De Luca et al., 2010; Sosnovsky and Dicheva, 2010].


2000s
[Purificato et al., 2024, §1.1]

16. EXPERT FINDING AND EXPERT PROFILING
These tracks within the Enterprise Track at
TREC 2005 [Craswell et al., 2005] constitutes a significant
turning point in user modeling and profiling research.
Advent of expertise retrieval research area [Balog et al., 2007].
2000s
[Purificato et al., 2024, §1.1]

17. RISE OF BEHAVIOR MODELING
Emphasis on personalization in various digital services,
particularly in recommenders, where researchers
developed advanced algorithms to analyze user behavior
and preferences for improved content personalization
[Abel et al., 2011; Lakiotaki et al., 2011;
Masthoff, 2011; Konstan and Riedl, 2012].2010-2015
Advent of expertise retrieval research area [Balog et al., 2007].
[Purificato et al., 2024, §1.1]

18. CONTEXT-AWARE USER MODELING
Aim to understand how user preferences and
behaviors change in different contexts.
This included factors such as location, time, and device,
leading to more adaptive and responsive system
[Adomavicius and Tuzhilin, 2011; Verbertet al., 2012;
Said et al., 2013; Codina et al., 2015].
RISE OF BEHAVIOR MODELING
Emphasis on personalization in various digital services,
, where researchers
user behavior
for improved content personalization
Abel et al., 2011; Lakiotaki et al., 2011;
.2010-2015
[Purificato et al., 2024, §1.1]

19. AWARE USER MODELING
user preferences and
behaviors change in different contexts.
This included factors such as location, time, and device,
leading to more adaptive and responsive system
[Adomavicius and Tuzhilin, 2011; Verbert et al., 2012;
.
DATA MINING APPROACHES
The ascent of big data drove the investigation of
advanced data mining techniques for user modeling
[Romero and Ventura, 2013; D’Oca and Hong, 2014;
van Dam and van de Velden, 2015].
2010-2015
[Purificato et al., 2024, §1.1]

20. MACHINE LEARNING AND
DEEP LEARNING APPROACHES
Large datasets have witnessed the application of
ML algorithms [Mercado et al., 2016; Shin, 2016;
Krishnan and Kamath, 2017; Lin et al., 2019]
and DL models [Gu et al., 2020; Wen et al., 2021;
Li et al., 2022; Wei et al., 2022] to unveil meaningful
patterns into user behaviors and automatically
learn user representations from raw data.
2016-2024
.
[Purificato et al., 2024, §1.1]

21. MULTIMODAL USER MODELS
These models aim to attain a comprehensive
understanding of user preferences and behaviors
by integrating information from various modalities
[Saevanee et al., 2015; Farseev et al., 2015; Guo et al., 2018].
2016-2024
[Purificato et al., 2024, §1.1]

22. ETHICAL CONSIDERATIONS AND
BEYOND-ACCURACY APPROACHES
Recent years have seen increasing needs
for privacy [Wu et al., 2021; Raber and Krüger, 2022; Liu et al., 2023],
transparency [Balog et al., 2019; Huang et al., 2019; Guesmi et al., 2022],
equity and fairness [Dai and Wang, 2021; Purificato et al., 2022;
Zheng et al., 2022; Abdelrazek et al., 2023; Celikok et al., 2023].
2016-2024
[Purificato et al., 2024, §1.1]

23. [Purificato et al., 2024, §2]

24. A representation of the preferences of any individual
user; roughly, it is a structured representation of the
user’s needs through which a retrieval system should,
e.g., act upon one or more goals based on that profile
and autonomously, pursuing the goals posed by the use.
[AmatoandStraccia,1999]
USER PROFILE
The procedure for gathering information on the
user’s interest; the system utilizes such information to
tailor services and improve the user’s satisfaction.
[Kanojeetal.,2015]
USER PROFILE
[Purificato et al., 2024, §2]

25. A representation of information about an
individual user that is essential for an adaptive
system to provide the adaptation effect.
[Brusilovskyetal.,2007]
USER MODEL
A data structure that is used to capture specific
characteristics about an individual user.
[PiaoandBreslin,2018]
USER MODEL
[Purificato et al., 2024, §2]

26. The process of acquiring, extracting,
and representing the features of users.
[Zhouetal.,2012]
USER PROFILINGUSER PROFILING
The process of inferring an individual’s interests,
personality traits, or behaviors from generated data
to create an efficient user representation, which
is exploited by adaptive and personalized systems.
[Ekeetal.,2019]
[Purificato et al., 2024, §2]

27. USER PROFILING
The process of automatically converting user information
into a predefined and interpretable format that reflects the
most important aspects of the user’s profile, which are
useful for further decision-making in practical applications.
[Voetal.,2021]
USER MODELING
The process of gathering information about a user’s
interests, constructing, maintaining, and using user profiles.
[Faridetal.,2018]
[Purificato et al., 2024, §2]

28. The process of building up and modifying a
conceptual understanding of the user. Its task is to
learn a latent representation for each user, with the
help of items and item features, with applications to
response prediction, recommendation, and other.
[LiandZhao,2020]
USER PROFILE MODELING
The process that constitutes the methodology for
building a user profile; it requires two steps to
describe: “what” has to be represented, and
“how” this information is effectively represented.
[AmatoandStraccia,1999]
USER MODELING
[Purificato et al., 2024, §2]

29. A user model (or user profile) is a structured
representation of an individual user’s
preferences, needs, behaviors, and demographic
details to personalize system interactions.
It is derived from direct user feedback or
inferred through machine learning and data
mining techniques. It supports the predictions of
future user intentions and the refinement of
systems response to enhance user satisfaction.
User models are often instrumental in optimizing
the relevance and efficiency of adaptive
systems, ensuring that user interactions are
aligned with individual needs and preferences.
[Purificatoetal.,2024]
NOVEL DEFINITIONS
[Purificato et al., 2024, §2]

30. NOVEL DEFINITIONS
User modeling (or user profiling) is the process of
acquiring, extracting, and representing user features
and personal characteristics to build accurate user
models (or user profiles).
It encompasses inferring personality traits and
behaviors from user-generated data. This dynamic
practice includes automatically converting user
information into interpretable formats, capturing latent
interests, and learning conceptual user representations.
Essentially, user modeling constitutes the methodology
for building and modifying user models, determining
“what” to represent and “how” to effectively represent
this information for adaptive and personalized systems.
[Purificatoetal.,2024]
[Purificato et al., 2024, §2]

31. PARADIGM
SHIFTS AND
NOVEL TRENDS
[Purificato et al., 2024, §3]

32. EXPLICIT USER MODELING
Also known as static or factual modeling,
required direct input from the user,
such as filling out a questionnaire or
completing an online form.
[Purificato et al., 2024, §3]

33. IMPLICIT USER MODELING
Initially used together with explicit methods,
modern systems shifted to passive collection and
analysis of dynamic user data, thus called
behavioral and adaptive modeling.
Static data still used by exploiting information
previously shared (e.g., social network accounts)
defining the novel pseudo-explicit user modeling.
[Purificato et al., 2024, §3]

34. DIRECT USER PREFERENCES
Traditionally, user preferences
and interests have been modelled
using explicit and direct feedback.
[Purificato et al., 2024, §3]

35. INDIRECT USER PREFERENCES
Everyday use of digital platforms and
reluctance of users in providing direct
feedback led to a growing emphasis on
capturing an individual’s preferences and
interests hidden in users’ historical behaviors.
[Purificato et al., 2024, §3]

36. USER
BEHAVIORAL
MODELINGMULTI-BEHAVIOR MODELING
Integrates various forms of user
interactions with items, rather than
relying on a single type of interaction.
MICRO AND MACRO
BEHAVIORAL MODELING
Respectively, the immediate actions that
a user takes reflecting short-term
preferences, and large-scale actions that
reflect a user’s long-term commitment.
SEQUENTIAL BEHAVIOR MODELING
Considers the order and timing of user actions
as influential for modifying user interests.
HIERARCHICAL USER PROFILING
Models users’ real-time interests at
various levels of granularity.
MOBILE USER PROFILING
Involves discerning users’ interests
and behavioral patterns based on
their activities on mobile devices.
[Purificato et al., 2024, §3]

37. SPECIFIC USER
REPRESENTATION
Scarcity of studies on generalized
user model representation.
Researchers tend to focus on
specific aspects of user modeling
rather than a holistic approach.
[Purificato et al., 2024, §3]

38. UNIVERSAL USER
REPRESENTATION
Create a unified and generalized
profile of a user by encapsulating
a broad spectrum of user behaviors
and preferences without bias toward
any specific task.
[Purificato et al., 2024, §3]

39. HOLISTIC USER MODELING
Integrates diverse and heterogeneous
personal data sources to construct a
comprehensive user representation.
any specific task.
[Purificato et al., 2024, §3]

40. GRAPH
DATA
STRUCTURES
KNOWLEDGE GRAPHS
Specific type of graph structure that
effectively represents complex information
by accumulating and conveying knowledge
of the real world, making them particularly
useful in several contexts.
GRAPH STRUCTURES
In the context of user modeling, graph
structures can be used to represent user
behavior, preferences, and interactions by
leveraging nodes and edges as, respectively,
the users and the relationships among them.
[Purificato et al., 2024, §3]

41. DEEP
LEARNING
These models have significantly
contributed to advancements in user
modeling research field, enabling more
accurate and comprehensive profiling
and prediction of user behavior.
Attention
Mechanism
Convolutional
Neural Networks
Autoencoders
Graph Neural
Networks
Recurrent
Neural Networks
Transformers
Long-Short
Term Memory
[Purificato et al., 2024, §3]

42. STANDARD APPLICATIONS
Versatile and valuable approaches
in many fields, particularly where
user-specific services are crucial, e.g.:
oRecommender Systems; ;
oE-commerce and Marketing;
oUser Interface Adaptation. .
[Purificato et al., 2024, §3]

43. CONTEMPORARY APPLICATIONS
Innovative approaches applied in
various important research fields to
tackle state-of-the-art challenges, e.g.:
oFake news detections;
oSocial Network analysis;
oCybersecurity.
[Purificato et al., 2024, §3]

44. BEYOND-
ACCURACY
PERSPECTIVES
Similar to the transformation observed in deep learning,
the incorporation of advanced techniques extending
beyond mere accuracy marks a significant global shift
in various domains, including user modeling. These
approaches prioritize fundamental values for humans,
e.g., privacy, fairness, and transparency.
[Purificato et al., 2024, §3]

45. Special Issue
“User Perspectives in
Human-Centered
Artificial Intelligence”
International Journal of
Human-Computer Studies (Q1)
Call for papers
Submission deadline:
November 18, 2024

46. CONTACTS
Erasmo Purificato
[email protected]
Ludovico Boratto
[email protected]
Ernesto W. De Luca
[email protected]
Resources

47. REFERENCES (1/5)
[Abdelrazeketal.,2023] Abdelrazek, M., Purificato, E., Boratto, L. and De Luca, E.W., 2023, July. Fairup: A framework for fairness analysis of graph neural network-based user
profiling models. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 3165-3169).
[Abeletal.,2011] Abel, F., Gao, Q., Houben, G.J. and Tao, K., 2011. Analyzing user modeling on twitter for personalized news recommendations. In User Modeling, Adaption and
Personalization: 19th International Conference, UMAP 2011, Girona, Spain, July 11-15, 2011. Proceedings 19 (pp. 1-12). Springer Berlin Heidelberg.
[AdomaviciusandTuzhilin,2011] Adomavicius, G. and Tuzhilin, A., 2010. Context-aware recommender systems. In Recommender systems handbook (pp. 217-253). Boston, MA:
Springer US.
[Allgayer et al., 1989] Allgayer, J., Harbusch, K., Kobsa, A., Reddig, C., Reithinger, N. and Schmauks, D., 1989. XTRA: a natural-language access system to expert systems.
International Journal of Man-Machine Studies, 31(2), pp.161-195.
[AmatoandStraccia,1999] Amato, G. and Straccia, U., 1999, September. User profile modeling and applications to digital libraries. In International conference on theory and
practice of digital libraries (pp. 184-197). Berlin, Heidelberg: Springer Berlin Heidelberg.
[Ardissono and Sestero, 1995] Ardissono, L. and Sestero, D., 1995. Using dynamic user models in the recognition of the plans of the user. User Modeling and User-Adapted
Interaction, 5, pp.157-190.
[Balogetal.,2007] Balog, K., Bogers, T., Azzopardi, L., De Rijke, M. and Van Den Bosch, A., 2007, July. Broad expertise retrieval in sparse data environments. In Proceedings of
the 30th annual international ACM SIGIR conference on Research and development in information retrieval (pp. 551-558).
[Balogetal.,2019] Balog, K., Radlinski, F. and Arakelyan, S., 2019, July. Transparent, scrutable and explainable user models for personalized recommendation. In Proceedings of
the 42nd international acm sigir conference on research and development in information retrieval (pp. 265-274).
[Brajnik and Tasso, 1994] Brajnik, G. and Tasso, C., 1994. A shell for developing non-monotonic user modeling systems. International Journal of Human-Computer Studies, 40(1),
pp.31-62.
[Brusilovsky, 2001] Brusilovsky, P., 2001. Adaptive hypermedia. User modeling and user-adapted interaction, 11, pp.87-110.
[Brusilovsky, 2004] Brusilovsky, P., 2004, May. KnowledgeTree: A distributed architecture for adaptive e-learning. In Proceedings of the 13th international World Wide Web
conference on Alternate track papers & posters (pp. 104-113).
[Brusilovsky et al., 1998] Brusilovsky, P., Kobsa, A. and Vassileva, J. eds., 1998.Adaptive hypertext and hypermedia. Dordrecht: Kluwer Academic.
[Brusilovsky and Maybury, 2002] Brusilovsky, P. and Maybury, M.T., 2002. From adaptive hypermedia to the adaptive web. Communications of the ACM, 45(5), pp.30-33.
[Brusilovskyetal.,2007] Brusilovski, P., Kobsa, A. and Nejdl, W. eds., 2007. The adaptive web: methods and strategies of web personalization (Vol. 4321). Springer Science &
Business Media.

48. REFERENCES (2/5)
[Caglayan et al., 1997] Caglayan, A., Snorrason, M., Jacoby, J., Mazzu, J., Jones, R. and Kumar, K., 1997. Learn sesame a learning agent engine. Applied Artificial Intelligence, 11(5),
pp.393-412.
[Celikoketal.,2023] Çelikok, M.M., Murena, P.A. and Kaski, S., 2023. Modeling needs user modeling. Frontiers in Artificial Intelligence, 6, p.1097891.
[Codinaetal.,2015] Codina, V., Mena, J. and Oliva, L., 2015. Context-aware user modeling strategies for journey plan recommendation. In User Modeling, Adaptation and
Personalization: 23rd International Conference, UMAP 2015, Dublin, Ireland, June 29-July 3, 2015. Proceedings 23 (pp. 68-79). Springer International Publishing.
[Cohen and Perrault, 1979] Cohen, P.R. and Perrault, C.R., 1979. Elements of a plan-based theory of speech acts. Cognitive science, 3(3), pp.177-212.
[Craswelletal.,2005] Craswell, N., De Vries, A.P. and Soboroff, I., 2005, November. Overview of the TREC 2005 Enterprise Track. In Trec (Vol. 5, pp. 1-7).
[D’OcaandHong,2014] D'Oca, S. and Hong, T., 2014. A data-mining approach to discover patterns of window opening and closing behavior in offices. Building and Environment,
82, pp.726-739.
[DaiandWang,2021] Dai, E. and Wang, S., 2021, March. Say no to the discrimination: Learning fair graph neural networks with limited sensitive attribute information. In
Proceedings of the 14th ACM International Conference on Web Search and Data Mining (pp. 680-688).
[De Bra et al., 1999] De Bra, P., Brusilovsky, P. and Houben, G.J., 1999. Adaptive hypermedia: from systems to framework. ACM Computing Surveys (CSUR), 31(4es), pp.12-es.
[DeLucaetal.,2010] De Luca, E.W., Plumbaum, T., Kunegis, J. and Albayrak, S., 2010, April. Multilingual Ontology-based User Profile Enrichment. In MSW (pp. 41-42).
[Ekeetal.,2019] Eke, C.I., Norman, A.A., Shuib, L. and Nweke, H.F., 2019. A survey of user profiling: State-of-the-art, challenges, and solutions. IEEE Access, 7, p.144907-144924.
[Faridetal.,2018] Farid, M., Elgohary, R., Moawad, I. and Roushdy, M., 2018, October. User profiling approaches, modeling, and personalization. In Proceedings of the 11th
international conference on informatics & systems (INFOS 2018).
[Farseevetal.,2015] Farseev, A., Nie, L., Akbari, M. and Chua, T.S., 2015, June. Harvesting multiple sources for user profile learning: a big data study. In Proceedings of the 5th
ACM on International Conference on Multimedia Retrieval (pp. 235-242).
[Finin and Drager, 1986] Finin, T. and Drager, D., 1986, May. GUMS: A general user modeling system. InProceedings of the Sixth Canadian Conference on Artificial Intelligence.
[Fink, 2004] Fink, J., 2004. User modeling servers: Requirements, design, and evaluation (Vol. 277). IOS Press.
[Fink and Kobsa, 2000] Fink, J. and Kobsa, A., 2000. A review and analysis of commercial user modeling servers for personalization on the world wide web. User modeling and
user-adapted interaction, 10, pp.209-249.
[Guetal.,2020] Gu, Y., Ding, Z., Wang, S. and Yin, D., 2020, January. Hierarchical user profiling for e-commerce recommender systems. In Proceedings of the 13th International
Conference on Web Search and Data Mining (pp. 223-231).
[Guesmietal.,2022] Guesmi, M., Chatti, M.A., Vorgerd, L., Ngo, T., Joarder, S., Ain, Q.U. and Muslim, A., 2022, July. Explaining user models with different levels of detail for
transparent recommendation: A user study. In Adjunct Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization (pp. 175-183).

49. REFERENCES (3/5)
[Guoetal.,2018] Guo, Y., Cheng, Z., Nie, L., Xu, X.S. and Kankanhalli, M., 2018, October. Multi-modal preference modeling for product search. In Proceedings of the 26th ACM
international conference on Multimedia (pp. 1865-1873).
[Huangetal.,2019] Huang, X., Fang, Q., Qian, S., Sang, J., Li, Y. and Xu, C., 2019, October. Explainable interaction-driven user modeling over knowledge graph for sequential
recommendation. In proceedings of the 27th ACM international conference on multimedia (pp. 548-556).
[Kanojeetal.,2015] Kanoje, S., Girase, S. and Mukhopadhyay, D., 2015. User profiling trends, techniques and applications. arXiv preprint arXiv:1503.07474.
[Kay, 1995] Kay, J., 1995. The um toolkit for cooperative user modelling.User Modelling and User-Adapted Interaction,4(3), pp.149-196.
[Kay et al., 2002] Kay, J., Kummerfeld, B. and Lauder, P., 2002. Personis: a server for user models. In Adaptive Hypermedia and Adaptive Web-Based Systems: Second
International Conference, AH 2002 Málaga, Spain, May 29–31, 2002 Proceedings 2 (pp. 203-212). Springer Berlin Heidelberg.
[Kobsa, 1990] Kobsa, A., 1990. Modeling the user's conceptual knowledge in BGP-MS, a user modeling shell system. Computational Intelligence, 6(4), pp.193-208.
[Kobsa, 2001] Kobsa, A., 2001. Generic user modeling systems. User modeling and user-adapted interaction, 11, pp.49-63.
[Kobsa, 2007] Kobsa, A., 2007. Generic user modeling systems.The adaptive web: Methods and strategies of web personalization, pp.136-154.
[Kobsa and Fink, 2006] Kobsa, A. and Fink, J., 2006. An LDAP-based user modeling server and its evaluation. User Modeling and User-Adapted Interaction, 16, pp.129-16.
[Kobsa and Pohl, 1994] Kobsa, A. and Pohl, W., 1994. The user modeling shell system BGP-MS. User Modeling and User-Adapted Interaction, 4, pp.59-106.
[Konstan et al., 1997] Konstan, J.A., Miller, B.N., Maltz, D., Herlocker, J.L., Gordon, L.R. and Riedl, J., 1997. GroupLens: applying collaborative filtering to Usenet news.
Communications of the ACM, 40(3), pp.77-87.
[KonstanandRiedl,2012] Konstan, J.A. and Riedl, J., 2012. Recommender systems: from algorithms to user experience. User modeling and user-adapted interaction, 22, p.101.
[KrishnanandKamath,2017] Krishnan, G.S. and Kamath, S.S., 2017, July. Dynamic and temporal user profiling for personalized recommenders using heterogeneous data
sources. In 2017 8th international conference on computing, communication and networking technologies (ICCCNT) (pp. 1-7). IEEE.
[Krulwich, 1997] Krulwich, B., 1997. Lifestyle finder: Intelligent user profiling using large-scale demographic data. AI magazine, 18(2), pp.37-37.
[Lakiotakietal.,2011] Lakiotaki, K., Matsatsinis, N.F. and Tsoukias, A., 2011. Multicriteria user modeling in recommender systems. IEEE Intelligent Systems, 26(2), pp.64-76.
[Langley, 1999] Langley, P., 1999, June. User modeling in adaptive interface. In UM99 User Modeling: Proceedings of the Seventh International Conference (pp. 357-370).
Vienna: Springer Vienna.
[LiandZhao,2020] Li, S. and Zhao, H., 2021, January. A survey on representation learning for user modeling. In Proceedings of the Twenty-Ninth International Conference on
International Joint Conferences on Artificial Intelligence (pp. 4997-5003).
[Lietal.,2022] Li, H., Dong, X., Cheng, L. and Mo, L., 2022, October. A Hierarchical User Behavior Modeling Framework for Cross-Domain Click-Through Rate Prediction. In
Proceedings of the 31st ACM International Conference on Information & Knowledge Management (pp. 4163-4167).

50. REFERENCES (4/5)
[Linetal.,2019] Lin, T.H., Gao, C. and Li, Y., 2019, July. Cross: Cross-platform recommendation for social e-commerce. In Proceedings of the 42nd International ACM SIGIR
conference on research and development in information retrieval (pp. 515-524).
[Liuetal.,2023] Liu, Q., Wu, J., Huang, Z., Wang, H., Ning, Y., Chen, M., Chen, E., Yi, J. and Zhou, B., 2023. Federated User Modeling from Hierarchical Information. ACM
Transactions on Information Systems, 41(2), pp.1-33.
[Masthoff,2011] Masthoff, J., 2010. Group recommender systems: Combining individual models. In Recommender systems handbook (pp. 677-702). Boston, MA: Springer US.
[Mehtaetal.,2005] Mehta, B., Niederee, C., Stewart, A., Degemmis, M., Lops, P. and Semeraro, G., 2005. Ontologically-enriched unified user modeling for cross-system
personalization. In User Modeling 2005: 10th International Conference, UM 2005, Edinburgh, Scotland, UK, July 24-29, 2005. Proceedings 10 (pp. 119-123). Springer Berlin.
[Mercadoetal.,2016] Mercado, I.T., Munaiah, N. and Meneely, A., 2016, November. The impact of cross-platform development approaches for mobile applications from the
user's perspective. In Proceedings of the International Workshop on App Market Analytics (pp. 43-49).
[Middletonetal.,2004] Middleton, S.E., Shadbolt, N.R. and De Roure, D.C., 2004. Ontological user profiling in recommender systems. ACM Transactions on Information Systems
(TOIS), 22(1), pp.54-88.
[Orwant, 1994] Orwant, J., 1994. Heterogeneous learning in the Doppelgänger user modeling system. User Modeling and User-Adapted Interaction, 4, pp.107-130.
[Paiva and Self, 1994] Paiva, A. and Self, J., 1994. TAGUS—A user and learner modeling workbench. User Modeling and User-Adapted Interaction, 4, pp.197-226.
[Peppers and Rogers, 1993] Peppers, D. and Rogers, M., 1993. The one to one future: Building relationships one customer at a time. New York: Currency Doubleday.
[Perrault et al., 1978] Perrault, C.R. and Allen, J., 1978. Speech acts as a basis for understanding dialogue coherence. In Theoretical issues in natural language processing.
[PiaoandBreslin,2018] Piao, G. and Breslin, J.G., 2018. Inferring user interests in microblogging social networks: a survey. User Modeling and User-Adapted Interaction, 28,
pp.277-329.
[Purificatoetal.,2022] Purificato, E., Boratto, L. and De Luca, E.W., 2022, October. Do graph neural networks build fair user models? assessing disparate impact and
mistreatment in behavioural user profiling. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management (pp. 4399-4403).
[Purificato et al., 2024] Purificato, E., Boratto, L. and De Luca, E.W., 2024. User Modeling and User Profiling: A Comprehensive Survey. arXiv preprint arXiv:2402.09660.
[RaberandKrüger,2022] Raber, F. and Krüger, A., 2022. Transferring recommendations through privacy user models across domains. User Modeling and User-Adapted
Interaction, 32(1), pp.25-90.
[Rich, 1979] Rich, E., 1979. User modeling via stereotypes. Cognitive science, 3(4), pp.329-354.
[RomeroandVentura,2013] Romero, C. and Ventura, S., 2013. Data mining in education. Wiley Interdisciplinary Reviews: Data mining and knowledge discovery, 3(1), pp.12-27.
[Saidetal.,2013] Said, A., Berkovsky, S. and De Luca, E.W., 2013. Introduction to special section on camra2010: Movie recommendation in context. ACM Transactions on
Intelligent Systems and Technology (TIST), 4(1), pp.1-9.

51. REFERENCES (5/5)
[Saevaneeetal.,2015] Saevanee, H., Clarke, N.L. and Furnell, S.M., 2012. Multi-modal behavioural biometric authentication for mobile devices. In Information Security and Privacy
Research: 27th IFIP TC 11 Information Security and Privacy Conference, SEC 2012, Heraklion, Crete, Greece, June 4-6, 2012. Proceedings 27 (pp. 465-474). Springer Berlin.
[Shin,2016] Shin, D.H., 2016. Cross-platform users’ experiences toward designing interusable systems. International Journal of Human-Computer Interaction, 32(7), pp.503-514.
[Siegetal.,2007] Sieg, A., Mobasher, B. and Burke, R., 2007, November. Web search personalization with ontological user profiles. In Proceedings of the sixteenth ACM
conference on Conference on information and knowledge management (pp. 525-534).
[Sleeman, 1985] Sleeman, D., 1985. UMFE: A user modelling front-end subsystem. International Journal of Man-Machine Studies, 23(1), pp.71-88.
[SosnovskyandDicheva,2010] Sosnovsky, S. and Dicheva, D., 2010. Ontological technologies for user modelling. International Journal of Metadata, Semantics and Ontologies,
5(1), pp.32-71.
[Trella et al., 2003] Trella, M., Conejo, R., Guzmán, E. and Bueno, D., 2003. An educational component based framework for web its development. InWeb Engineering:
International Conference, ICWE 2003 Oviedo, Spain, July 14–18, 2003 Proceedings 3(pp. 134-143). Springer Berlin Heidelberg.
[vanDamandvandeVelden,2015] Van Dam, J.W. and Van De Velden, M., 2015. Online profiling and clustering of Facebook users. Decision Support Systems, 70, pp.60-72.
[Verbertetal.,2012] Verbert, K., Manouselis, N., Ochoa, X., Wolpers, M., Drachsler, H., Bosnic, I. and Duval, E., 2012. Context-aware recommender systems for learning: a survey
and future challenges. IEEE transactions on learning technologies, 5(4), pp.318-335.
[Voetal.,2021] Vo, D.V., Karnjana, J. and Huynh, V.N., 2021. An integrated framework of learning and evidential reasoning for user profiling using short texts.Information
Fusion,70, pp.27-42.
[Wahlster and Kobsa, 1989] Wahlster, W. and Kobsa, A., 1989. User models in dialog systems. User models in dialog systems, pp.4-34.
[Weietal.,2022] Chu, Y.W., Hosseinalipour, S., Tenorio, E., Cruz, L., Douglas, K., Lan, A. and Brinton, C., 2022, October. Mitigating biases in student performance prediction via
attention-based personalized federated learning. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management (pp. 3033-3042).
[Wenetal.,2021]Wen, H., Zhang, J., Lv, F., Bao, W., Wang, T. and Chen, Z., 2021, July. Hierarchically modeling micro and macro behaviors via multi-task learning for conversion
rate prediction. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 2187-2191).
[Wuetal.,2021] Wu, J., Liu, Q., Huang, Z., Ning, Y., Wang, H., Chen, E., Yi, J. and Zhou, B., 2021, April. Hierarchical personalized federated learning for user modeling. In
Proceedings of the Web Conference 2021 (pp. 957-968).
[Zhengetal.,2022] Zheng, Z., Qiu, Z., Xu, T., Wu, X., Zhao, X., Chen, E. and Xiong, H., 2022, April. CBR: context bias aware recommendation for debiasing user modeling and
click prediction. In Proceedings of the ACM Web Conference 2022 (pp. 2268-2276).
[Zhouetal.,2012] Zhou, X., Xu, Y., Li, Y., Josang, A. and Cox, C., 2012. The state-of-the-art in personalized recommender systems for social networking. Artificial Intelligence
Review, 37, pp.119-132.