Journal article
Bag of works retrieval: TFIDF weighting of works co-cited with a seed
International journal on digital libraries, v 19(2-3)
01 Sep 2018
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
Although not presently possible in any system, the style of retrieval described here combines familiar components-co-citation linkages of documents and TF*IDF weighting of terms-in a way that could be implemented in future databases. Rather than entering keywords, the user enters a string identifying a work-a seed-to retrieve the strings identifying other works that are co-cited with it. Each of the latter is part of a "bag of works," and it presumably has both a co-citation count with the seed and an overall citation count in the database. These two counts can be plugged into a standard formula for TF*IDF weighting such that all the co-cited items can be ranked for relevance to the seed, given that the entire retrieval is relevant to it by evidence from multiple co-citing authors. The result is analogous to, but different from, traditional "bag of words" retrieval, which it supplements. Some properties of the ranking are illustrated by works co-cited with three seeds: an article on search behavior, an information retrieval textbook, and an article on centrality in networks. While these are case studies, their properties apply to bag of works retrievals in general and have implications for users (e.g., humanities scholars, domain analysts) that go beyond any one example.
Metrics
Details
- Title
- Bag of works retrieval: TFIDF weighting of works co-cited with a seed
- Creators
- Howard D. White - Drexel University
- Publication Details
- International journal on digital libraries, v 19(2-3)
- Publisher
- Springer Nature
- Number of pages
- 11
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- [Retired Faculty]
- Web of Science ID
- WOS:000441741300004
- Scopus ID
- 2-s2.0-85019600240
- Other Identifier
- 991019169602304721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Web of Science research areas
- Information Science & Library Science