scinapse is loading now...

Using collaborative filtering to weave an information tapestry

Published on Dec 1, 1992in Communications of The ACM 3.06
· DOI :10.1145/138859.138867
David A. Goldberg27
Estimated H-index: 27
(PARC),
David A. Nichols5
Estimated H-index: 5
(PARC)
+ 1 AuthorsDouglas B. Terry19
Estimated H-index: 19
(PARC)
Abstract
The Tapestry experimental mail system developed at the Xerox Palo Alto Research Center is predicated on the belief that information filtering can be more effective when humans are involved in the filtering process. Tapestry was designed to support both content-based filtering and collaborative filtering, which entails people collaborating to help each other perform filtering by recording their reactions to documents they read. The reactions are called annotations; they can be accessed by other people’s filters. Tapestry is intended to handle any incoming stream of electronic documents and serves both as a mail filter and repository; its components are the indexer, document store, annotation store, filterer, little box, remailer, appraiser and reader/browser. Tapestry’s client/server architecture, its various components, and the Tapestry query language are described.
  • References (11)
  • Citations (2886)
Cite
References11
Newest
Published on Jun 2, 1992 in International Conference on Management of Data
Douglas B. Terry19
Estimated H-index: 19
(PARC),
David A. Goldberg27
Estimated H-index: 27
(PARC)
+ 1 AuthorsBrian M. Oki2
Estimated H-index: 2
(PARC)
In a database to which data is continually added, users may wish to issue a permanent query and be notified whenever data matches the query. If such continuous queries examine only single records, this can be implemented by examining each record as it arrives. This is very efficient because only the incoming record needs to be scanned. This simple approach does not work for queries involving joins or time. The Tapestry system allows users to issue such queries over a database of mail and bulleti...
440 Citations Source Cite
Published on Dec 2, 1990in ACM Sigois Bulletin
Ernst Lutz1
Estimated H-index: 1
,
Hans V. Kleist-Retzow1
Estimated H-index: 1
,
Karl Hoernig1
Estimated H-index: 1
The main goal in the design of intelligent information processing systems is to provide automatic support for the processing of the large amount of documents, today's office workers are confronted with. Existing message filtering systems can provide this support only if the messages to be processed are at least semi-structured.The MAFIA System (MAil-FIlter-Agent) overcomes these limitations of existing message filtering systems by providing an automatic document classification component which re...
38 Citations Source Cite
Published on Jan 1, 1990
Douglas B. Terry1
Estimated H-index: 1
9 Citations
Published on Aug 29, 1988 in Very Large Data Bases
Jack Kent1
Estimated H-index: 1
,
Douglas B. Terry1
Estimated H-index: 1
,
Willie-Sue Orr1
Estimated H-index: 1
A database management system provides the ideal support for electronic mail applications. The Walnut mail system built at the Xerox Palo Alto Research Center was recently redesigned to take better advantage of its underlying database facilities. The ability to pose ad-hoc queries with a "fill-in-the-form" browser allows people to browse their mail quickly and effectively, while database access paths guarantee fast retrieval of stored information. Careful consideration of the systems' usage was r...
12 Citations
Published on Jul 1, 1988in ACM Transactions on Information Systems 1.77
Stephen Pollock1
Estimated H-index: 1
(bell northern research)
Much computerized support for knowledge workers has consisted of tools to handle low-level functions such as distribution, storage, and retrieval of information. However, the higher level processes of making decisions and taking actions with respect to this information have not been supported to the same degree. This paper describes the ISCREEN prototype system for screening text messages. ISCREEN includes a high-level interface for users to define rules, a component that screens text messages, ...
124 Citations Source Cite
Published on Oct 1, 1987
Jonathan Rosenberg7
Estimated H-index: 7
(Carnegie Mellon University),
Craig F. Everhart2
Estimated H-index: 2
(Carnegie Mellon University),
Nathaniel S. Borenstein13
Estimated H-index: 13
(Carnegie Mellon University)
lIntroduction This paper provides an overview of the Andrew Message System, which is in operation within the Andrew project at Carnegie Mellon University. The Andrew environment currently consists of 300 highfunction workstations (typified by the IBM RT-PC) each running Berkeley Unix and attached to a large campus-wide network. A central file system provides transparently the appearance of a large, monolithic Unix file system. In addition, there are approximately 600 IBM PC’s and 300 (University...
98 Citations Source Cite
Published on May 1, 1987in Communications of The ACM 3.06
Thomas W. Malone53
Estimated H-index: 53
(Massachusetts Institute of Technology),
Kenneth R. Grant6
Estimated H-index: 6
(Massachusetts Institute of Technology)
+ 2 AuthorsMichael D. Cohen27
Estimated H-index: 27
(University of Michigan)
The Information Lens system is a prototype intelligent information-sharing system that is designed to include not only good user interfaces for supporting the problem-solving activity of individuals, but also good organizational interfaces for supporting the problem-solving activities of groups.
603 Citations Source Cite
Published on Jan 1, 1987
M. Darnovsky1
Estimated H-index: 1
,
G. W. Bowman1
Estimated H-index: 1
49 Citations
Published on Dec 1, 1985 in Symposium on Operating Systems Principles
David K Gifford D K59
Estimated H-index: 59
(Massachusetts Institute of Technology),
Robert W. Baldwin2
Estimated H-index: 2
(Massachusetts Institute of Technology)
+ 1 AuthorsJohn M. Lucassen5
Estimated H-index: 5
(Massachusetts Institute of Technology)
63 Citations Source Cite
Published on Nov 1, 1984
Jacob Palme13
Estimated H-index: 13
34 Citations
Cited By2886
Newest
Chang-Dong Wang14
Estimated H-index: 14
(Sun Yat-sen University),
Zhi Hong Deng1
Estimated H-index: 1
(Sun Yat-sen University)
+ 1 AuthorsPhilip S. Yu110
Estimated H-index: 110
(University of Illinois at Chicago)
Collaborative filtering (CF) algorithms have been widely used to build recommender systems since they have distinguishing capability of sharing collective wisdoms and experiences. However, they may easily fall into the trap of the Matthew effect, which tends to recommend popular items and hence less popular items become increasingly less popular. Under this circumstance, most of the items in the recommendation list are already familiar to users and therefore the performance would seriously degen...
2 Citations Source Cite
Published on Jul 1, 2019in Expert Systems With Applications 3.77
Tu Minh Phuong10
Estimated H-index: 10
(Posts and Telecommunications Institute of Technology),
Do Thi Lien2
Estimated H-index: 2
(Posts and Telecommunications Institute of Technology),
Nguyen Duy Phuong3
Estimated H-index: 3
(Posts and Telecommunications Institute of Technology)
Abstract Context-aware recommender systems (CARS) are specially designed to take into account the contextual conditions under which a user experiences an item, with the goal of generating improved recommendations. A known difficulty when constructing recommender systems is data sparseness, which reduces the effectiveness of collaborative filtering algorithms. While using contextual information provides fine-grained signals for the recommendation process, it makes the data even sparser and increa...
Source Cite
Published on Jul 1, 2019in Knowledge Based Systems 4.40
Jiangzhou Deng (College of Management and Economics), Junpeng Guo (College of Management and Economics), Yong Wang (Chongqing University of Posts and Telecommunications)
Abstract Data sparsity is a widespread problem of collaborative filtering (CF) recommendation algorithms. However, some common CF methods cannot adequately utilize all user rating information; they are only able to use a small part of the rating data, depending on the co-rated items, which leads to low prediction accuracy. To alleviate this problem, a novel K-medoids clustering recommendation algorithm based on probability distribution for CF is proposed. The proposed scheme makes full use of al...
Source Cite
Tian Qiu9
Estimated H-index: 9
(Nanchang Hangkong University),
Chi Wan1
Estimated H-index: 1
(Nanchang Hangkong University)
+ 1 AuthorsZi-Ke Zhang10
Estimated H-index: 10
(Hangzhou Normal University)
Abstract Four real recommender system datasets, the Netflix , SMovieLens , LMovieLens and RYM datasets, are analyzed to gain an insight into their user interest characteristics. A preference of active users to cold objects and a diverse interest of inactive users are revealed, which characteristics are introduced to improve the personalized recommendation algorithms. Based on seven different algorithms, we propose a general improvement formula for them, and finally four new algorithms are obtain...
Source Cite
Published on Jun 2, 2019 in North American Chapter of the Association for Computational Linguistics
Johannes Bjerva6
Estimated H-index: 6
(University of Groningen),
Yova Kementchedjhieva2
Estimated H-index: 2
+ 1 AuthorsIsabelle Augenstein12
Estimated H-index: 12
(University of Copenhagen)
In the principles-and-parameters framework, the structural features of languages depend on parameters that may be toggled on or off, with a single parameter often dictating the status of multiple features. The implied covariance between features inspires our probabilisation of this line of linguistic inquiry---we develop a generative model of language based on exponential-family matrix factorisation. By modelling all languages and features within the same architecture, we show how structural sim...
Published on Jun 27, 2018in Neural Processing Letters 1.79
Yang Weng (Sichuan University), Lei Wu (Sichuan University), Wenxing Hong (Xiamen University)
Variational approximation method finds wide applicability in approximating difficult-to-compute probability distributions, a problem that is especially important in Bayesian inference to estimate posterior distributions. Latent factor model is a classical model-based collaborative filtering approach that explains the user-item association by characterizing both items and users on latent factors inferred from rating patterns. Due to the sparsity of the rating matrix, the latent factor model usual...
Source Cite
Traditional methods for solving linear systems have quickly become impractical due to an increase in the size of available data. Utilizing massive amounts of data is further complicated when the data is incomplete or has missing entries. In this work, we address the obstacles presented when working with large data and incomplete data simultaneously. In particular, we propose to adapt the Stochastic Gradient Descent method to address missing data in linear systems. Our proposed algorithm, the Sto...
Source Cite
Published on May 28, 2019in arXiv: Databases
Source Cite
Published on May 14, 2019in Journal of Intelligent and Fuzzy Systems 1.43
Malathi Devarajan2
Estimated H-index: 2
(Shanmugha Arts, Science),
N. Sabiyath Fatima1
Estimated H-index: 1
+ 1 AuthorsLogesh Ravi3
Estimated H-index: 3
(Shanmugha Arts, Science)
3 Citations Source Cite