Towards recency ranking in web search

Dong, Anlei; Chang, Yi; Zheng, Zhaohui; Mishne, Gilad; Bai, Jing; Zhang, Ruiqiang; Buchner, Karolina; Liao, Ciya; Dı́az, Fernando

doi:10.1145/1718487.1718490

Cited by 131 publications

(135 citation statements)

References 20 publications

Supporting

Mentioning

134

Contrasting

Order By: Relevance

“…older or newer). This behavior is different from the observed in other search services, such as in news search, where recent and updated information is preferred [19]; (2) highly relevant documents for a topic may exist throughout the entire search period, despite being known that some periods tend to concentrate more relevant documents [20]. -topical relevance for a given navigational topic.…”

Section: Relevance Propagationmentioning

confidence: 65%

Evaluating Web Archive Search Systems

Costa

Silva

2012

Web Information Systems Engineering - WISE 2012

View full text Add to dashboard Cite

Abstract. The information published on the web, a representation of our collective memory, is rapidly vanishing. At least 77 web archives have been developed to cope with the web's transience problem, but despite their technology having achieved a good maturity level, the retrieval effectiveness of the search services they provide still presents unsatisfactory results. In this work, we propose an evaluation methodology for web archive search systems based on a list of requirements compiled from previous characterizations of web archives and their users. The methodology includes the design of a test collection and the selection of evaluation measures to support realistic and reproducible experiments. The test collection enabled, for the first time, to measure the effectiveness of state-of-the-art IR technology employed in web archives. Results confirm the poor quality of search results retrieved with such technology. However, we show how to combine temporal features, along with the regular topical features, to improve the search effectiveness on web archives. The test collection is available to the research community.

show abstract

Section: Relevance Propagationmentioning

confidence: 65%

Evaluating Web Archive Search Systems

Costa

Silva

2012

Web Information Systems Engineering - WISE 2012

View full text Add to dashboard Cite

show abstract

“…But also in settings such as the web search engines where interactions are frequent and rich profiles are typically available, our approach has large potential value. The problem of fast changing content is well-known [66]. Perhaps the fraction of new users is small, yet they may be important enough to warrant extra effort, think of new users considering a search engine switch [239].…”

Section: Resultsmentioning

confidence: 99%

“…Unfortunately, query-level satisfaction metrics ignore the information about a user's 'journey' from a question to an answer which might take more than one query [120]. Al-Maskari et al [14] claim that query-level satisfaction is not applicable for informational queries -users can run follow-up queries if they are unsatisfied with the returned results; reformulations can lead users to an answer; this scenario is called task-level user satisfaction [66,97]. Previous research proposed different methods for identifying successful sessions: Hassan et al [97] used a Markov model to predict success at the end of the task; Ageev et al [9] exploited an expertise-dependent difference in search behavior by using a Conditional Random Fields model to predict a search success -authors used a game-like strategy for collecting annotated data by asking participants to find answers to non-trivial questions using web search.…”

Section: Evaluating User Satisfactionmentioning

confidence: 99%

Using Contextual Information to Understand Searching and Browsing Behavior

Kiseleva

2015

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

View full text Add to dashboard Cite

“…Temporal aspects have gained traction in information retrieval (IR) over the last couple of years and have found applications in document ranking [7,6,9], query completion [22], query understanding [15,8,17], and recommender systems [24,5,21]. Shokouhi et al [22] analyse temporal trends and also use forecasted frequencies to suggest candidates for auto completion in web search.…”

Section: Related Workmentioning

confidence: 99%

“…More specifically, they propose a temporal link-based ranking scheme, which also incorporates features from historical author activities. Dong et al identify breaking news queries by training a learning to rank model with temporal features extracted from a page index such as the time stamp of when the page was created, last updated, or linked to [8]. Elsas et al analyzed the temporal dynamics of content changes in order to rank documents for navigational queries [10].…”

Section: Related Workmentioning

confidence: 99%

Timely Semantics: A Study of a Stream-Based Ranking System for Entity Relationships

Fischer

Blanco

Mika

et al. 2015

The Semantic Web - ISWC 2015

View full text Add to dashboard Cite

In recent years, search engines have started presenting se-mantically relevant entity information together with document search results. Entity ranking systems are used to compute recommendations for related entities that a user might also be interested to explore. Typically, this is done by ranking relationships between entities in a semantic knowledge graph using signals found in a data source as well as type annotations on the nodes and links of the graph. However, the process of producing these rankings can take a substantial amount of time. As a result, entity ranking systems typically lag behind real-world events and present relevant entities with outdated relationships to the search term or even outdated entities that should be replaced with more recent relations or entities. This paper presents a study using a real-world stream-processing based implementation of an entity ranking system, to understand the effect of data timeliness on entity rankings. We describe the system and the data it processes in detail. Using a longitudinal case-study, we demonstrate (i) that low-latency, large-scale entity relationship ranking is feasible using moderate resources and (ii) that stream-based entity ranking improves the freshness of related entities while maintaining relevance. Abstract. In recent years, search engines have started presenting semantically relevant entity information together with document search results. Entity ranking systems are used to compute recommendations for related entities that a user might also be interested to explore. Typically, this is done by ranking relationships between entities in a semantic knowledge graph using signals found in a data source as well as type annotations on the nodes and links of the graph. However, the process of producing these rankings can take a substantial amount of time. As a result, entity ranking systems typically lag behind real-world events and present relevant entities with outdated relationships to the search term or even outdated entities that should be replaced with more recent relations or entities. This paper presents a study using a real-world stream-processing based implementation of an entity ranking system, to understand the effect of data timeliness on entity rankings. We describe the system and the data it processes in detail. Using a longitudinal case-study, we demonstrate (i) that low-latency, large-scale entity relationship ranking is feasible using moderate resources and (ii) that stream-based entity ranking improves the freshness of related entities while maintaining relevance.

show abstract

Towards recency ranking in web search

Cited by 131 publications

References 20 publications

Evaluating Web Archive Search Systems

Evaluating Web Archive Search Systems

Using Contextual Information to Understand Searching and Browsing Behavior

Timely Semantics: A Study of a Stream-Based Ranking System for Entity Relationships

Contact Info

Product

Resources

About