Open Conal-Tuohy opened 1 year ago
Would it be possible to craft a query that would reliably return the full set of relevant articles? Or would it be better to create a Trove List or similar data structure which could be generated automatically but still be manually editable to deal with special cases?
Note that the "Inky Way" column is not necessarily zoned as a single article in Trove but can appear as a part of a large article, following the "The Inky Way" heading.
Is this a case for using "To Be Continued"?
Roger Osbourne from JCU has a dream to research the history of Australian journalism contained with a regular column of the Bulletin called "The Inky Way".
Can the content of this column be extracted automatically?
Can the content be parsed into a structured form such as a knowledge graph using some NLP technique?