Searching online book documents and analyzing book citations

Abstract

Academic search engines and digital libraries provide convenient online search and access facilities for scientific publications. However, most existing systems do not include books in their collections although several books are freely available online. Academic books are different from papers in terms of their length, contents and structure. We argue that accounting for academic books is important in understanding and assessing scientific impact. We introduce an open-book search engine that extracts and indexes metadata, contents, and bibliography from online PDF book documents. To the best of our knowledge, no previous work gives a systematical study on building a search engine for books.We propose a hybrid approach for extracting title and authors from a book that combines results from CiteSeer, a rule based extractor, and a SVM based extractor, leveraging web knowledge. For "table of contents" recognition, we propose rules based on multiple regularities based on numbering and ordering. In addition, we study bibliography extraction and citation parsing for a large dataset of books. Finally, we use the multiple fields available in books to rank books in response to search queries. Our system can effectively extract metadata and contents from large collections of online books and provides efficient book search and retrieval facilities.

Knowledge models from PDF textbooks

“…P start contains the first 50 pages in P. Previous work (Z. Wu, Das, et al, 2013; used the first 20 pages of the book for this step, but we found textbooks where that margin is not enough. The first TOC page is added to P toc , which is the list containing all pages of the TOC.…”

A survey on scholarly data: From big data perspective

“…Wu et al [10] described the use of SVM-based metadata extraction (SVMHeaderParse [56]) for CiteSeerX. However, this method is known to work poorly for metadata extraction of books [72].…”

“…Wu et al [56] gave a hybrid approach using SVMbased extractor and rule-based extractor for extracting authors and title of a book. Two sections that differentiate books from other scholarly documents is the presence of table of contents (TOC) [108] and indexes [106] [107], usually present at the back of the book.…”

Can back-of-the-book indexes be automatically created?

“…So on this dataset we cannot consider the location of index terms, but only serve the evaluation as a keyword extraction task. Books in the second dataset was collected from the Citeseer repository, most of which are in computer science and engineering [21]. We manually select 213 books with good quality back-of-the-book index.…”