You are invited to participate in the upcoming 7th workshop on Bibliometric-enhanced Information Retrieval (BIR), to be held as part of the 40th European Conference on Information Retrieval (ECIR). https://www.ecir2018.org/
Keynote title of Cyril Labbé: "Trends in Gaming Indicators: On Failed Attempts at Deception and their Computerised Detection"
Abstract: Counting articles and citations, analyzing citations and co-authors graphs have become ways to assess researchers and institutions performance. Fairly enough, these measures are becoming targets for institutions and individual researchers thus triggering new behaviors. As a matter of fact, scientometrics and informetrics systems of all kinds have to separate the grain form the chaff. Among others, fields like Information Retrieval, network analysis and natural language processing may offers answers to deal with this kind of problems. Through several emblematic case studies (fake researcher, generated papers, paper mills), we show evidences of attempts to game indicators together with automatic ways to detect them (automatic detection of generated papers, errors detection).
Keynote title of Ralf Schenkel: "Integrating and exploiting public metadata sources in a bibliographic information system"
Abstract: Bibliographic information systems need to rely on metadata provided by various sources in various forms and with various quality. The talk gives some insights how the dblp bibliography as an example for such a system is maintained and improved. It shows how metadata can be automatically harvested from publisher websites and how the harvesting process can be steered. It also discusses some open sources of bibliographic metadata and how they can be used to enrich existing bibliographic data, but also how varying their quality is.
|9:30||Introduction by organizers||Editorial | Slides (2.1 MB)|
|9:40||Cyril Labbé (Keynote)||Trends in Gaming Indicators: On Failed Attempts at Deception and their Computerised Detection |
Paper | Slides (4.4 MB)
|10:30||Maria Janina Sarol, Linxi Liu and Jodi Schneider||Testing a Citation and Text-Based Framework for Retrieving Publications for Literature Reviews |
Paper | Slides (4.3 MB)
|11:30||Anaïs Ollagnier, Sébastien Fournier and Patrice Bellot||BIBLME RecSys: Harnessing Bibliometric Measures for Scholarly Paper Recommender System |
Paper | Slides (2.3 MB)
|12.00||André Rattinger, Jean-Marie Le Goff and Christian Guetl||Local Word Embeddings for Query Expansion based on Co-Authorship and Citations |
Paper | Slides (342 KB)
|12:30||Mario Cataldi, Luigi Di Caro and Claudio Schifanella|
|14.30||Ralf Schenkel (Keynote)||Integrating and exploiting public metadata sources in a bibliographic information system|
Paper | Slides (3.8 MB)
|15:30||Marc Bertin and Iana Atanassova||InTeReC : an In-text Reference corpus for applying Natural language processing to Bibliometrics|
Paper | Slides (4.7 MB)
|16:30||Ameni Kacem Sahraoui and Philipp Mayr||Users are not influenced by high impact and core journals while searching|
Paper | Slides (610 KB)
|18:00||End of the workshop|
Bibliometric techniques are not yet widely used to enhance retrieval processes in search systems, although they offer value-added effects for users. In this workshop we will explore how statistical modelling of scholarship, such as Bradfordizing or network analysis of coauthorship network, or simple citation graphs, can improve retrieval services for specific communities, as well as for large, cross-domain collections like Mendeley. This workshop aims to raise awareness of the missing link between Information Retrieval (IR) and bibliometrics/scientometrics and to create a common ground for the incorporation of bibliometric-enhanced services into retrieval at the scholarly search engine interface.
See proceedings of the former BIR workshops at ECIR 2014 <http://ceur-ws.org/Vol-1143/>, ECIR 2015 <http://ceur-ws.org/Vol-1344/>, ECIR 2016 <http://ceur-ws.org/Vol-1567/>, ECIR 2017 <http://ceur-ws.org/Vol-1823/>, JCDL 2016 <http://ceur-ws.org/Vol-1610/> and SIGIR 2017 <http://ceur-ws.org/Vol-1888/>.
In this 7th workshop we aim to engage with the IR community about possible links to bibliometrics and complex network theory which also explores networks of scholarly communication. Bibliometric techniques are not yet widely used to enhance retrieval processes, yet they offer value-added effects for users. Our interests include information retrieval, information seeking, science modelling, network analysis, and natural language processing. The goal is to apply insights from bibliometrics, scientometrics, and informetrics to concrete practical problems of information retrieval and browsing.
Retrieval evaluations have shown that simple text-based retrieval methods scale up well but do not progress. Traditional retrieval has reached a high level in terms of measures like precision and recall, but scientists and scholars still face challenges present since the early days of digital libraries: mismatches between search terms and indexing terms, overload from result sets that are too large and complex, and the drawbacks of text-based relevance rankings. Therefore we will focus on statistical modelling and corresponding visualizations of the evolving science system. Such analyses have revealed not only the fundamental laws of Bradford and Lotka, but also network structures and dynamic mechanisms in scientific production. Statistical models of scholarly activities are increasingly used to evaluate specialties, to forecast and discover research trends, and to shape science policy. Their use as tools in navigating scientific information in search systems is a promising but still relatively new development. We will explore how statistical modelling of scholarship can improve retrieval services for specific communities, as well as for large, cross-domain collections. Some of these techniques are already used in working systems but not well integrated in larger scholarly IR environments.
The availability of new IR test collections that contain citation and bibliographic information like the iSearch collection or the ACL collection could deliver enough ground to interest (again) the IR community in these kind of bibliographic systems. The long-term research goal is to develop and evaluate new approaches based on informetrics and bibliometrics.
The aim of this workshop is to bring together researchers and practitioners from different domains, such as information retrieval, information seeking, science modelling, bibliometrics, scientometrics, network analysis, natural language processing, digital libraries, and approaches to visualize search and retrieval to move toward a deeper understanding of this research challenge.
To support the previously described goals the workshop topics include (but are not limited to) the following:
We especially invite descriptions of running projects and ongoing work. Papers that investigate multiple themes directly are especially welcome.
All submissions must be written in English following Springer LNCS author guidelines (6 to 12 pages) and should be submitted as PDF files to EasyChair. All submissions will be reviewed by at least two independent reviewers. Please be aware of the fact that at least one author per paper needs to register for the workshop and attend the workshop to present the work. In case of no-show the paper (even if accepted) will be deleted from the proceedings AND from the program.
Workshop proceedings will be deposited online in the CEUR workshop proceedings publication service (ISSN 1613-0073) - This way the proceedings will be permanently available and citable (digital persistent identifiers and long term preservation).