Information Filtering Based on User Behavior Analysis and Best Match Text Retrieval

Morita, Masahiro; Shinoda, Yoichi

doi:10.1007/978-1-4471-2099-5_28

Cited by 250 publications

(198 citation statements)

References 0 publications

Supporting

Mentioning

187

Contrasting

Unclassified

Order By: Relevance

“…The similarity between decision times for judging positively or extremely negatively against a document prohibits the use of such a metric from any further studies. Further to this, we were also impressed by the low reading times, which are in stark contrast with other studies that are concerned with the average reading time of a web document, such as [28], [27]. Other studies report average reading times closer to the ones we experiences, but again higher [29], [30], although these were not based on web documents.…”

Section: Discussion and Future Workcontrasting

confidence: 59%

“…Therefore it is apparent that the use of time as a metric is not a reliable source of information, since there is not much significant discrepancy between the average reading times for each feedback score. This observation brought about the decision to eliminate this metric from the weight recalculation formula, as it is in contrast with other findings, such as those by Morita [28] and Claypool [27], but seem to confirm Kelly's [29] conclusion that reading time is an unreliable source for implicit relevance feedback. …”

Section: Feedback Ratingsmentioning

confidence: 57%

See 1 more Smart Citation

A calendar based Internet content pre-caching agent for small computing devices

Komninos

Dunlop

2007

Pers Ubiquit Comput

View full text Add to dashboard Cite

We described in earlier publications the principles of a system where internet content would be pre-cached, based on contextual information obtained from a user's electronic calendar. The model for such a system envisioned a set of cooperating agents, distributed on a user's desktop and mobile device, which would be responsible for making decisions on the context and preferences of the user, and downloading the relevant internet content through a land-based broadband connection and storing it on the mobile device. This paper presents and discusses established pre-caching techniques and their suitability for use on mobile information access scenarios. It proceeds in describing the implementation details of an alternative approach, a calendarbased pre-caching system and presents the findings of tests that were made with human subjects on such a system.

show abstract

Section: Discussion and Future Workcontrasting

confidence: 59%

Section: Feedback Ratingsmentioning

confidence: 57%

A calendar based Internet content pre-caching agent for small computing devices

Komninos

Dunlop

2007

Pers Ubiquit Comput

View full text Add to dashboard Cite

show abstract

“…To tackle those problems, two approaches have been proposed [3,29,21,23]. The first approach is to condense the user/item rating matrix through dimensionality reduction techniques such as Singular Value Decomposition (SVD) [3,29].…”

Section: Introductionmentioning

confidence: 99%

“…The second approach is to "enrich" the user/item rating matrix by 1) introducing default ratings or implicit user ratings, e.g., the time spent on reading articles [23]; 2) using half-baked rating predictions from content-based methods [21]; or 3) exploiting transitive associations among users through their past transactions and feedback [12]. These methods improve the performance of recommender systems to some extent.…”

Section: Introductionmentioning

confidence: 99%

A Social Network-Based Recommender System (SNRS)

Chu

2010

Annals of Information Systems

214

116

View full text Add to dashboard Cite

Abstr act. Social influence plays an important role in product marketing. However, it has rarely been considered in traditional recommender systems. In this paper we present a new paradigm of recommender systems which can utilize information in social networks, including user preferences, item's general acceptance, and influence from social friends. A probabilistic model is developed to make personalized recommendations from such information. We extract data from a real online social network, and our analysis of this large dataset reveals that friends have a tendency to select the same items and give similar ratings. Experimental results on this dataset show that our proposed system not only improves the prediction accuracy of recommender systems but also remedies the data sparsity and coldstart issues inherent in collaborative filtering. Furthermore, we propose to improve the performance of our system by applying semantic filtering of social networks, and validate its improvement via a class project experiment. In this experiment we demonstrate how relevant friends can be selected for inference based on the semantics of friend relationships and finer-grained user ratings. Such technologies can be deployed by most content providers. Intr oductionIn order to overcome information overload, recommender systems have become a key tool for providing users with personalized recommendations on items such as movies, music, books, news, and web pages. Intrigued by many practical applications, researchers have developed algorithms and systems over the last decade. Some of them have been commercialized by online venders such as Amazon.com, Netflix.com, and IMDb.com. These systems predict user preferences (often represented as numeric ratings) for new items based on the user's past ratings on other items. There are typically two types of algorithms for recommender systems --content-based methods and collaborative filtering. Content-based methods measure the similarity of the recommended item (target item) to the ones that a target user (i.e., user who receives recommendations) likes or dislikes [25,22,30] based on item attributes. On the other hand, collaborative filtering finds users with tastes that are similar to the target user's based on their past ratings. Collaborative filtering will then make recommendations to the target user based on the opinions of those similar users [3,5,27].Despite all of these efforts, recommender systems still face many challenging problems. First, there are demands for further improvements on the prediction ac-

show abstract

“…The GroupLens project experimented with time-spent-reading as an implicit rating for Usenet news articles . Building on the work by Morita and Shinoda (1994) that showed that users spent more time reading articles they preferred, the GroupLens project was able to show that collaborative filtering was able to predict ratings for substantially more articles by using time-spent-reading and that the ratings predicted were of similar quality to explicit ratings-based predictions.…”

Section: Focusing Implicit Ratingsmentioning

confidence: 99%