Language intent models for inferring user browsing behavior

Tsagkias, Manos; Blanco, Roi

doi:10.1145/2348283.2348330

Cited by 8 publications

(7 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our experiments mainly prove the point that the referrer domain has a big predictive potential that should be considered when building any browsing user model. As our goal is limited to the prediction of the next page visited, more general content-based techniques for cold-start [1,27] are not directly comparable with our approach, although a more extensive comparison would be valuable to gain a broader view on the problem. At any rate, we hope the findings highlighted in this paper lead to a greater consideration of the referrer domain with particular focus on cold-start problems.…”

Section: Resultsmentioning

confidence: 99%

“…There are approaches based on models of similarity among news articles [16,10,20] considering different key factors like textual similarity, recency, coherence, novelty and popularity. Tsagkias and Blanco [26] proposed a language intent model that extracts a query from the user browsing session. In this way they model the user interest using the queries of the users.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Cold-start news recommendation with domain-dependent browse graph

Trevisiol

Aiello

Schifanella

et al. 2014

Proceedings of the 8th ACM Conference on Recommender Systems

View full text Add to dashboard Cite

Online social networks and mash-up services create opportunities to connect different web services otherwise isolated. Specifically in the case of news, users are very much exposed to news articles while performing other activities, such as social networking or web searching. Browsing behavior aimed at the consumption of news, especially in relation to the visits coming from other domains, has been mainly overlooked in previous work. To address that, we build a BrowseGraph out of the collective browsing traces extracted from a large viewlog of Yahoo News (0.5B entries) and we define the ReferrerGraph as its subgraph induced by the sessions with the same referrer domain. The structural and temporal properties of the graph show that browsing behavior in news is highly dependent on the referrer URL of the session, in terms of type of content consumed and time of consumption. We build on this observation and propose a news recommender that addresses the cold-start problem: given a user landing on a page of the site for the first time, we aim to predict the page she will visit next. We compare 24 flavors of recommenders belonging to the families of contentbased, popularity-based, and browsing-based models. We show that the browsing-based recommender that takes into account the referrer URL is the best performing, achieving a prediction accuracy of 48% in conditions of heavy data sparsity.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Cold-start news recommendation with domain-dependent browse graph

Trevisiol

Aiello

Schifanella

et al. 2014

Proceedings of the 8th ACM Conference on Recommender Systems

View full text Add to dashboard Cite

show abstract

“…Specifically, in the last years there was a surge of interest in the BrowseGraph, a graph where the nodes are web pages and the edges represent the transitions from one page to another made by the navigation of the users. Characterizing the browsing behavior of users is a valuable source of information for a number of different tasks, ranging from understanding how people's search behaviors differ [32], ranking webpages through search trails [1,33] or recommending content items using past history [29]. A comparison between the standard hyperlink graph, based on the structure of the network, with the browse graph built by the users' navigation patterns, has been made by Liu et al [22,23].…”

Section: Browsegraphmentioning

confidence: 99%

Local Ranking Problem on the BrowseGraph

Trevisiol

Aiello

Boldi

et al. 2015

Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval

Self Cite

View full text Add to dashboard Cite

The "Local Ranking Problem" (LRP) is related to the computation of a centrality-like rank on a local graph, where the scores of the nodes could significantly differ from the ones computed on the global graph. Previous work has studied LRP on the hyperlink graph but never on the BrowseGraph, namely a graph where nodes are webpages and edges are browsing transitions. Recently, this graph has received more and more attention in many different tasks such as ranking, prediction and recommendation. However, a webserver has only the browsing traffic performed on its pages (local BrowseGraph) and, as a consequence, the local computation can lead to estimation errors, which hinders the increasing number of applications in the state of the art. Also, although the divergence between the local and global ranks has been measured, the possibility of estimating such divergence using only local knowledge has been mainly overlooked. These aspects are of great interest for online service providers who want to: (i) gauge their ability to correctly assess the importance of their resources only based on their local knowledge, and (ii) take into account real user browsing fluxes that better capture the actual user interest than the static hyperlink network. We study the LRP problem on a BrowseGraph from a large news provider, considering as subgraphs the aggregations of browsing traces of users coming from different domains. We show that the distance between rankings can be accurately predicted based only on structural information of the local graph, being able to achieve an average rank correlation as high as 0.8.

show abstract

“…White et al (2009) examined five types of contextual information in website recommendation while Ye et al (2012) further explored social influence on item recommendation. Moreover, Tsagkias and Blanco (2012) concentrated on analyzing users' browsing behavior on news articles, and Jin (2012) recommended contents through a unified, per-sonalized messaging system. In our work, the accumulated social interaction content is utilized to help determine the interest of future reader.…”

Section: Related Workmentioning

confidence: 99%

Interest Analysis Using Semantic PageRank and Social Interaction Content

Huang

2013

2013 IEEE 13th International Conference on Data Mining Workshops

View full text Add to dashboard Cite

Abstract-Social media has long been a popular resource for sentiment analysis and data mining. In this paper, we learn to predict reader interest after article reading using social interaction content in social media. The abundant interaction content (e.g., reader feedback) aims to replace typically private reader profile and browse history. Our method involves estimating interest preferences with respect to article topics and identifying quality social content concerning informativity. During interest analysis, we combine and transform articles and their reader responses into PageRank word graph to balance author-and reader-end influence. Semantic features of words, such as their content sources (authors vs. readers), syntactic parts-of-speech, and degrees of references (i.e., significances) among authors and readers, are used to weight PageRank word graph. We present the prototype system, InterestFinder, that applies the method to reader interest prediction by calculating word interestingness scores. Two sets of evaluation show that traditional, local PageRank can more accurately cover more span of reader interest with the help of topical interest preferences learned globally, word nodes' semantic information, and, most important of all, quality social interaction content such as reader feedback.

show abstract

Language intent models for inferring user browsing behavior

Cited by 8 publications

References 25 publications

Cold-start news recommendation with domain-dependent browse graph

Cold-start news recommendation with domain-dependent browse graph

Local Ranking Problem on the BrowseGraph

Interest Analysis Using Semantic PageRank and Social Interaction Content

Contact Info

Product

Resources

About