scispace - formally typeset
Search or ask a question
Proceedings ArticleDOI

Comparison of Personalised Systems

TL;DR: The characteristics and advantages of user profiling and why it is so essential in today's world, with specific reference to internet usage are put forth and which factors of the usage should be taken into consideration and the importance of these factors in user profiling are explained.
Abstract: Personalization is omnipresent everywhere in today's modern world applications. It is primarily employed to improve user experience by adapting and learning from the patterns and information extracted from the user. There are various methods of making a system learn from the user behaviour. This paper gives a review of some of the techniques used for user profiling and personalisation systems. The paper puts forth the characteristics and advantages of user profiling and why it is so essential in today's world, with specific reference to internet usage. It also explains which factors of the usage should be taken into consideration and the importance of these factors in user profiling. The paper elaborates on the studied techniques with respect to internet usage because of its ever-growing nature, complexity in learning from the vast source, adapting to changes in usage patterns and the ultimate objective of providing a better user experience while being on-line. The commonality and differences in various proposed techniques are also summarised and highlighted.
Citations
More filters
Journal ArticleDOI
TL;DR: The results show that although traditional methods have been continuously improved, they are not sufficient to unleash the full potential of large-scale user reviews, especially the use of heterogeneous data for multi-dimensional user profiling.
Abstract: With the extensive development of big data and social networks, the user profile field has received much attention. User profiling is essential for understanding the characteristics of various users, contributing to better understanding of their requirements in specific scenarios. User-generated contents which directly reflect people’s thoughts and intention are a valuable source for profiling users, among which user reviews by nature are invaluable sources for acquiring user requirements and have drawn increasing attention from both academia and industry. However, review-based user profiling (RBUP), as an emerging research direction, has not been systematically reviewed, hindering researchers from further investigation. In this work, we carry out a systematic mapping study on review-based user profiling, with an emphasis on investigating the generic analysis process of RBUP and identifying potential research directions. Specifically, 51 out of 2478 papers were carefully selected for investigation under a standardized and systematic procedure. By carrying out in-depth analysis over such papers, we have identified a generic process that should be followed to perform review-based user profiling. In addition, we perform multi-dimensional analysis on each step of the process in order to review current research progress and identify challenges and potential research directions. The results show that although traditional methods have been continuously improved, they are not sufficient to unleash the full potential of large-scale user reviews, especially the use of heterogeneous data for multi-dimensional user profiling.

6 citations

Proceedings ArticleDOI
01 Nov 2018
TL;DR: A software architecture is proposed that simplifies the creation of early design models from requirements and facilitates effective communication between technical designers and stakeholders and various personalized learning software systems from different contexts to the proposed architecture.
Abstract: This paper addresses issues associated with requirements for personalized learning systems and their software architecture. These systems aim to provide unique learning experiences through adapting to a variable set of learners' characteristics at different levels of sophistication in many various contexts using a broad range of technologies. The diversity in personalized learning systems makes it difficult to represent user requirements in a way that software designers are able to use directly. Identifying a process to implement effectively personalized learning software systems remains a serious challenge. We propose a software architecture that simplifies the creation of early design models from requirements and facilitates effective communication between technical designers and stakeholders. First, we define general concepts of personalized learning software systems, and then elaborate a reusable software architecture for personalized learning software systems that can be used in different contexts. Finally, we map various personalized learning software systems from different contexts to the proposed architecture.

3 citations

References
More filters
Proceedings ArticleDOI
15 Aug 2005
TL;DR: It is concluded that clicks are informative but biased, and while this makes the interpretation of clicks as absolute relevance judgments difficult, it is shown that relative preferences derived from clicks are reasonably accurate on average.
Abstract: This paper examines the reliability of implicit feedback generated from clickthrough data in WWW search. Analyzing the users' decision process using eyetracking and comparing implicit feedback against manual relevance judgments, we conclude that clicks are informative but biased. While this makes the interpretation of clicks as absolute relevance judgments difficult, we show that relative preferences derived from clicks are reasonably accurate on average.

1,484 citations

Journal ArticleDOI
Udi Manber1, Ash Patel1, John Robison1
TL;DR: This artcle, focusing on three examples of personalization: My Yahoo!, Yahoo! Companion, and Inside Yahoo! Search, focuses on My Yahoo! (my.yahoo.com), a customized personal copy of Yahoo!.
Abstract: COMMUNICATIONS OF THE ACM August 2000/Vol. 43, No. 8 35 In this artcle, we concentrate on three examples of personalization: My Yahoo!, Yahoo! Companion, and Inside Yahoo! Search. My Yahoo! (my.yahoo.com) is a customized personal copy of Yahoo!. Users can select from hundreds of modules, such as news, stock prices, weather, and sports scores, and place them on one or more Web pages. The actual content for each module is then updated automatically, so users can see what they want to see in the order they want to see it. This provides users with the latest information on every subject, but with only the specific items they want to know about. An example of a My Yahoo! page (with Yahoo! Companion) is shown in the accompanying figure. Space limitations prevent us from describing its many features; instead, we mention a few general issues:

254 citations

Proceedings ArticleDOI
26 Sep 2010
TL;DR: An overview of the differentiating characteristics of explicit and implicit feedback using datasets mined from Last.fm, an online music station and recommender service, and techniques for extracting user preferences from both are presented.
Abstract: Explicit and implicit feedback exhibits different characteristics of users' preferences with both pros and cons. However, a combination of these two types of feedback provides another paradigm for recommender systems (RS). Their combination in a user preference model presents a number of challenges but can also overcome the problems associated with each other. In order to build an effective RS on combination of both types of feedback, we need to have comparative data allowing an understanding of the computation of user preferences. In this paper, we provide an overview of the differentiating characteristics of explicit and implicit feedback using datasets mined from Last.fm, an online music station and recommender service. The datasets consisted of explicit positive feedback (by loving tracks) and implicit feedback which is inherently positive (the number of times a track is played). Rather than relying on just one type of feedback, we present techniques for extracting user preferences from both. In order to compare and contrast the performances of these techniques, we carried out experiments using the Taste recommender system engine and the Last.fm datasets. Our results show that implicit and explicit positive feedback complements each other, with similar performances despite their different characteristics.

190 citations


Additional excerpts

  • ...(2) Comparison of Implicit and Explicit Feedback from an Online Music Recommendation Service- Jawaheer et....

    [...]

Proceedings ArticleDOI
09 Sep 2012
TL;DR: This paper presents a computationally effective approach for the direct minimization of a ranking objective function, without sampling, and demonstrates by experiments on the Y!Music and Netflix data sets that the proposed method outperforms other implicit feedback recommenders in many cases in terms of the ErrorRate, ARP and Recall evaluation metrics.
Abstract: Two flavors of the recommendation problem are the explicit and the implicit feedback settings. In the explicit feedback case, users rate items and the user-item preference relationship can be modelled on the basis of the ratings. In the harder but more common implicit feedback case, the system has to infer user preferences from indirect information: presence or absence of events, such as a user viewed an item. One approach for handling implicit feedback is to minimize a ranking objective function instead of the conventional prediction mean squared error. The naive minimization of a ranking objective function is typically expensive. This difficulty is usually overcome by a trade-off: sacrificing the accuracy to some extent for computational efficiency by sampling the objective function. In this paper, we present a computationally effective approach for the direct minimization of a ranking objective function, without sampling. We demonstrate by experiments on the Y!Music and Netflix data sets that the proposed method outperforms other implicit feedback recommenders in many cases in terms of the ErrorRate, ARP and Recall evaluation metrics.

181 citations


"Comparison of Personalised Systems" refers background in this paper

  • ...(3) Alternating Least Squares for Personalized Ranking – Takacs et....

    [...]

Book ChapterDOI
TL;DR: This chapter studies the main issues regarding user profiles from the perspectives of these research fields, and examines what information constitutes a user profile; how the user profile is represented; how it is acquired and built; and how the profile information is used.

166 citations