Expert Finding Systems: A Systematic Review (original) (raw)
Related papers
TOWARDS A MULTI-FEATURE ENABLED APPROACH FOR OPTIMIZED EXPERT SEEKING
With the enormous growth of data, retrieving information from the Web became more desirable and even more challenging because of the Big Data issues (e.g. noise, corruption, bad quality…etc.). Expert seeking, defined as returning a ranked list of expert researchers given a topic, has been a real concern in the last 15 years. This kind of task comes in handy when building scientific committees, requiring to identify the scholars' experience to assign them the most suitable roles in addition to other factors as well. Due to the fact the Web is drowning with plenty of data, this opens up the opportunity to collect different kinds of expertise evidence. In this paper, we propose an expert seeking approach with specifying the most desirable features (i.e. criteria on which researcher's evaluation is done) along with their estimation techniques. We utilized some machine learning techniques in our system and we aim at verifying the effectiveness of incorporating influential features that go beyond publications.
Data-driven Techniques for Expert Finding
Proceedings of the 9th International Conference on Agents and Artificial Intelligence, 2017
In this work, we propose enhanced data-driven techniques that optimize expert representation and identify subject experts via automated analysis of the available online information. We use a weighting method to assess the levels of expertise of an expert to the domain-specific topics. An expert profile is presented by a description of the topics in which the person is an expert plus the relative levels (weights) of knowledge or experience he/she has in the different topics. In this context, we define a way to estimate the expertise similarity between experts. Then the experts finding task is viewed as a list completion task and techniques that return similar experts to ones provided by the user are considered. The proposed techniques are tested and evaluated on data extracted from PubMed repository.
A Community-based Expert Finding System
2007
Abstract This paper proposes a system to facilitate exchange of information by automatically finding experts, competent in answering a given question. Our objective is to provide an online tool, which enables individuals within a potentially large organization to search for experts in a certain area, which may not be represented in company organization or reporting lines.
The expertfinder corpus 2007 for the benchmarking and development of expertfinding systems
2007
We provide a benchmark dataset for expert finding within the computer science domain. We show how large isolated data graphs from disparate structured data sources can be combined to form one, large, well-linked RDF graph and implement these methods to achieve our dataset. Such a graph lends itself to links analysis and thus opens up possibilities for analysis by expert finding techniques.
Expert finder systems – design and use
2011
The survey aimed at investigating how companies deal with the challenge of sharing of employees' expert knowledge. We wanted to find out which tools are being used to register, communicate and search employees as a knowledge resource. Specifically, we wanted to know how service organizations use expert finder systems to share knowledge about employees' knowledge, interest, competences and activities. The purpose of the survey was to provide insight into goals, content and functionality of expert finder systems, including updating strategies and connection to social media knowledge sharing tools, for example LinkedIn, Twitter, Facebook, Lotus Quickr, RSS feed.
High quality expertise evidence for expert search
2008
In an Enterprise setting, an expert search system can assist users with their “expertise need” by suggesting people with relevant expertise to the topic of interest. These systems typically work by associating documentary evidence of expertise to each candidate expert, and then ranking the candidates by the extent to which the documents in their profile are about the query.
Information Processing & Management, 2014
Expertise seeking is the activity of selecting people as sources for consultation about an information need. This review of 72 expertise-seeking papers shows that across a range of tasks and contexts people, in particular work-group colleagues and other strong ties, are among the most frequently used sources. Studies repeatedly show the influence of the social network -of friendships and personal dislikes -on the expertise-seeking network of organisations. In addition, people are no less prominent than documentary sources, in work contexts as well as daily-life contexts. The relative influence of source quality and source accessibility on source selection varies across studies. Overall, expertise seekers appear to aim for sufficient quality, composed of reliability and relevance, while also attending to accessibility, composed of access to the source and access to the source information. Earlier claims that seekers disregard quality to minimise effort receive little support. Source selection is also affected by task-related, seeker-related, and contextual factors. For example, task complexity has been found to increase the use of information sources whereas task importance has been found to amplify the influence of quality on source selection. Finally, the reviewed studies identify a number of barriers to expertise seeking. 1 preferable to other types of sources. We prefer the term expertise seeking because it better includes these considerations than terms such as expert seeking and people finding. Third, the source is selected for consultation about an information need, thereby distinguishing expertise seeking from activities aimed at initiating extended collaboration rather than consultation. This distinction is somewhat malleable but, for example, excludes staff hiring from expertise seeking as defined in this review. Fourth, expertise seeking differs from expertise retrieval (in ways similar to how information seeking differs from information retrieval). Expertise seeking concerns the psychological, social, and organisational aspects of how people select other people as sources. Conversely, expertise retrieval addresses the algorithmic aspects of linking people to expertise areas in order to provide technological support for the identification of people sources. For reviews of expertise retrieval, see and . provides a framework of expertise seeking. The framework, a result of this review, illustrates that an expertise seeker's selection of one out of several possible sources is affected by selection criteria, aims to satisfy an information need, takes place in a context, and may face barriers. The review first considers which sources are selected, then turns to the multiple factors that influence the source-selection process as implicit or explicit selection criteria, and finally addresses barriers to expertise seeking. In more detail, the review covers eight topics: 1. Ranking of information sources: Are people among the sources most frequently used? What are the most frequently used people sources? 2. People versus documentary sources: How are people and documentary sources balanced against each other? What factors affect this balance? 3. Internal versus external sources: How are sources internal to a seeker's organisation balanced against external sources? 4. Quality versus accessibility: Is the selection of people as sources determined by source quality, source accessibility, or both? Which components constitute quality and accessibility?
The Open University at TREC 2006 Enterprise Track Expert Search Task
2006
The Multimedia and Information Systems group at the Knowledge Media Institute of the Open University participated in the Expert Search task of the Enterprise Track in TREC 2006. We have proposed to address three main innovative points in a two-stage language model, which consists of a document relevance model and a cooccurrence model, in order to improve the performance of expert search. The three innovative points are based on characteristics of documents. First, document authority in terms of their PageRanks is considered in the document relevance model. Second, document internal structure is taken into account in the co-occurrence model. Third, we consider multiple levels of associations between experts and query terms in the co-occurrence model. Our experiments on the TREC2006 Expert Search task show that addressing the above three points has led to improved effectiveness of expert search on the W3C dataset.