Search Engine Journal

Google Book Search & TextRank

Although the technology Google uses for ranking the results and indexing of the books in the Google Book Search project is still a bit unknown, Bill Slawski has put together some interesting research that points to TextRank, which was co-invented by Professor Rada Mihalcea.

Professor Mihalcea received a grant of $107,112 from Google which helped her with research involving “automatic extraction methods to retrieve significant information in books stored in electronic format.” Mihalcea is also listed as a co-inventor of the ‘TextRank’ patent.

Bill continues with his search engine detective work “If you are familiar with pagerank and Kleinberg’s Hyperlinked Induced Topic Search (HITS), and Wordnet, you might find the patent application’s description of how textrank would work interesting.”

My first tormenting thought after reading this is whether or not Google Book Search and TextRank is going to result in publishers and copy editors taking SEO into consideration before putting works into print and granting Google Print access to scan and index their works. Will it come to this?