Combining bibliometrics, information retrieval, and relevance theory, Part 1: First examples of a synthesis: Research Articles

• Authors: Howard D. White
• Venue: Journal of the American Society for Information Science and Technology
• Year: 2007

In Sperber and Wilson's relevance theory (RT), the ratio CognitiveEffects-Processing Effort defines the relevance of a communication.The tf*idf formula from information retrieval is used tooperationalize this ratio for any item co-occurring with auser-supplied seed term in bibliometric distributions. The tfweight of the item predicts its effect on the user in the contextof the seed term, and its idf weight predicts the user's processingeffort in relating the item to the seed term. The idf measure, alsoknown as statistical specificity, is shown to haveunsuspected applications in quantifying interrelated concepts suchas topical and nontopical relevance, levels of user expertise, andlevels of authority. A new kind of visualization, the pennantdiagram, illustrates these claims. The bibliometric distributionsvisualized are the works cocited with a seed work (MobyDick), the authors cocited with a seed author (White HD,for maximum interpretability), and the books and articles cocitedwith a seed article (S.A. Harter's Psychological Relevance andInformation Science, which introduced RT to information scientistsin 1992). Pennant diagrams use bibliometric data and informationretrieval techniques on the system side to mimic arelevance-theoretic model of cognition on the user side. Relevancetheory may thus influence the design of new visual informationretrieval interfaces. Generally, when information retrieval andbibliometrics are interpreted in light of RT, the implications arerich: A single sociocognitive theory may serve to integrateresearch on literature-based systems with research on their users,areas now largely separate. © 2007 Wiley Periodicals, Inc.