Broad expertise retrieval in sparse data environments

Balog, Krisztian; Bogers, Toine; Azzopardi, Leif; Rijke, Maarten de; Bosch, Antal van den

doi:10.1145/1277741.1277836

Cited by 101 publications

(93 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The data set we use for experimental evaluation is the UvT Expert Collection [6]. It was collected from a publicly accessible database of employees involved in research or teaching at Tilburg University (UvT), The Netherlands.…”

Section: Methodsmentioning

confidence: 99%

“…For example, instead of capturing the associations at the document level, they may be estimated at the paragraph or snippet level [7,20,24]. Other extensions incorporate additional forms of evidence through the use of priors [14], document structure [33], hierarchical, organizational, and topical context and structure [6,23], and Web data [25].…”

Section: Related Workmentioning

confidence: 99%

“…The key idea behind the model is to simulate how a user may search for experts using a standard document search engine: first, finding documents which are relevant, and then, examining each of these documents for associated persons. By scanning through a number of documents the user can obtain an idea of which people are more likely to be experts on the query topic [6].…”

Section: Baseline Modelmentioning

confidence: 99%

“…Expert finding addresses the task of identifying the right person with the appropriate skills and knowledge [6]. Experts can be required for a variety of purposes: problem solving, question answering, providing more detailed information on a topic, to name a few.…”

Section: Introductionmentioning

confidence: 99%

“…The main focus has been on developing content-based algorithms, similar to document search. State-of-the-art expertise retrieval algorithms identify experts based on the content of documents that they are associated with [6,19,26]. While these approaches have been very effective in finding the most knowledgeable people on a given topic, they abstract away from the actual user performing the search.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A User-Oriented Model for Expert Finding

Смирнова

Balog

2011

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Expert finding addresses the problem of retrieving a ranked list of people who are knowledgeable on a given topic. Several models have been proposed to solve this task, but so far these have focused solely on returning the most knowledgeable people as experts on a particular topic. In this paper we argue that in a real-world organizational setting the notion of the "best expert" also depends on the individual user and her needs. We propose a user-oriented approach that balances two factors that influence the user's choice: time to contact an expert, and the knowledge value gained after. We use the distance between the user and an expert in a social network to estimate contact time, and consider various social graphs, based on organizational hierarchy, geographical location, and collaboration, as well as the combination of these. Using a realistic test set, created from interactions of employees with a university-wide expert search engine, we demonstrate substantial improvements over a state-of-the-art baseline on all retrieval measures.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Baseline Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A User-Oriented Model for Expert Finding

Смирнова

Balog

2011

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

Integrating multiple windows and document features for expert finding

Zhu

Song

Rüger

2009

J. Am. Soc. Inf. Sci.

View full text Add to dashboard Cite

Expert finding is a key task in enterprise search and has recently attracted lots of attention from both research and industry communities. The Text REtrieval Conference 2 (TREC) has organized an expert search task for 2005, 2006, and 2007. Given a search topic, a prominent existing approach is to apply some information retrieval (IR) system to retrieve top ranking documents, which will then be used to derive associations between experts and the search topic based on co occurrences. However, we argue that expert finding is more sensitive to multiple document features that current expert finding systems insufficiently address, including: (1) multiple levels of associations between experts and search topics, (2) document internal structure and (3) document authority. We propose a novel approach which integrates the above three aspects as well as a query expansion technique in a two stage model for expert finding. A systematic evaluation is conducted on the TREC2006 and TREC2005 expert search collections to test the performance of our approach and the effects of different aspects of document features and query expansion. These experimental results show that query expansion can dramatically improve expert finding performance.Both document internal structure and our novel multiple window based approach for taking into account multiple levels of associations improve expert finding over the direct use of a number of well known IR models for both with and without query expansion. KeywordsExpert finding, enterprise search 1 Correspondence author.

show abstract

Contextual factors for finding similar experts

Hofmann¹,

Balog²,

Bogers³

et al. 2010

J. Am. Soc. Inf. Sci.

Self Cite

View full text Add to dashboard Cite

Expertise-seeking research studies how people search for expertise and choose whom to contact in the context of a specific task. An important outcome are models that identify factors that influence expert finding. Expertise retrieval addresses the same problem, expert finding, but from a system-centered perspective. The main focus has been on developing content-based algorithms similar to document search. These algorithms identify matching experts primarily on the basis of the textual content of documents with which experts are associated. Other factors, such as the ones identified by expertise-seeking models, are rarely taken into account. In this article, we extend content-based expert-finding approaches with contextual factors that have been found to influence human expert finding. We focus on a task of science communicators in a knowledge-intensive environment, the task of finding similar experts, given an example expert. Our approach combines expertise-seeking and retrieval research. First, we conduct a user study to identify contextual factors that may play a role in the studied task and environment. Then, we design expert retrieval models to capture these factors. We combine these with content-based retrieval models and evaluate them in a retrieval experiment. Our main finding is that while content-based features are the most important, human participants also take contextual factors into account, such as media experience and organizational structure. We develop two principled ways of modeling the identified factors and integrate them with contentbased retrieval models. Our experiments show that models combining content-based and contextual factors can significantly outperform existing content-based models. Received March 16, 2009; revised November 19, 2009; accepted November 19, 2009 1 This is an expanded and revised version of Hofmann, Balog, Bogers, & de Rijke, 2008. IntroductionThe increasing amount of information available is making the need to criticially assess information more important. The burden of credibility assessment and quality control is partly shifting onto individual information seekers, but the need for information intermediaries (e.g., experts) has not disappeared and is actually increasing in cases where the credibility of information has to meet high standards (Metzger, 2007). Against this background, expert finding is a particularly relevant task: identifying and selecting individuals with specific expertise, for example, to help with a task or solve a problem. Expert finding has been addressed from different viewpoints, including expertise retrieval, which takes a mostly system-centered approach, and expertise seeking, which studies related human aspects.The goal of expertise retrieval is to support search for experts using information-retrieval technology. Following the experimental paradigm and evaluation framework established in the information-retrieval community, expertise retrieval has been addressed in world-wide evaluation efforts (Craswell, de Vries, & Soboroff, 2006...

show abstract

Broad expertise retrieval in sparse data environments

Cited by 101 publications

References 17 publications

A User-Oriented Model for Expert Finding

A User-Oriented Model for Expert Finding

Integrating multiple windows and document features for expert finding

Contextual factors for finding similar experts

Contact Info

Product

Resources

About