Computers

Professor's algorithm writes technical reports, romance novels could be next

Philip M. Parker has created a computerized system to automatically compile data into book form (Image: Shutterstock)
Philip M. Parker has created a computerized system to automatically compile data into book form (Image: Shutterstock)

Philip M. Parker, a marketing professor at INSEAD (the European Institute of Business Administration), has written and patented a system that uses an algorithm to automatically compile data into book form. Between his works and those of his research group (ICON Group International), he has over 900,000 books currently for sale on Amazon. More than a smart search engine, his system only requires a few minutes or a few hours to scan the databases relevant to any given topic and organize that data into a technical report. Next stop? Romance novels.

There are few things in life quite as boring as writing a technical report. You accumulate all available data on the topic, then categorize and prioritize the information. A general structure within with which to present the data is then chosen from a few common structures, whereupon the collected and sorted information is presented as a report. Such reports are formulaic – produced in accordance with a slavishly followed rule or style, and their generation is largely a process of intellectual drudgery requiring very little creativity. It's exactly the sort of task for which computers were developed.

Prof. Parker, an author of several conventionally written technical and business reports, realized one day that the process of writing such a report can be described in terms of a reasonably well defined algorithm. He then set out to program a computer to carry out this algorithm, for which he was issued US Patent 7,266,767 (Method and apparatus for automated authoring and marketing.).

Parker designed the algorithm to follow (hopefully closely) the path that an expert would take in writing a summary about a data-rich subject. There are similarities to IBM's Jeopardy grandmaster Watson, which also casts a wide data net, then organizes and summarizes the data so it can respond rapidly to questions.

Some examples of books written by Parker's program include:

  • Satirists: Webster's Quotations, Facts and Phrases

  • The 2007 Report on Little Cigarette-Size Cigars Weighing Less Than 3 Pounds Per 1,000 Cigars: World Market Segmentation by City
  • Webster's English to Portuguese Brazilian Crossword Puzzles: Level 10 (Portuguese Edition)
  • Webster's Hiligaynon - English Thesaurus Dictionary
  • The Official Patient's Sourcebook on Blepharitis
  • While some of these titles seem difficult to believe, there is a (generally small) market for each of them. If a person or company needs in-depth data about a subject, however narrow, that data has value in organized form. Parker's program works especially well with modern distribution technologies, turning print-on-demand into written-on-demand.

    Parker has also used an outgrowth of his algorithm to write a comprehensive set of poems about roughly 80,000 words in the English language. Totopoetry is a collection of algorithmically authored poetry that neatly illustrates the strengths and limitations of algorithmic writing. Poems are written in 17 styles (e.g., Haiku, limerick, sonnet) for each word in English.

    Each poem is intended to illuminate the meaning of the word on which it is based. For example, the octosyllable poem for "poetry" reads:

             "Really instant and overt.
            &nbspBut; also distant and covert."
    Totopoetry

    And then there is the modern Haiku form, again on "poetry":

             "An executive,
            &nbspevokes; many directions,
            &nbspnumbers; and manners"
    Totopoetry

    At present Parker's algorithm cannot judge its work against some intrinsic or personal measure of poetic merit.

    The next area of formulaic writing to which Parker wants to adapt his algorithm is romance novels, which are widely (perhaps unfairly) denigrated as "cookie-cutter" literature. Parker believes their simplicity and limited plot structure suggest romances as the best target for an early attack on fiction writing. Regardless of his level of success, human authors are likely to face progressively more competition from algorithmic authors over the next decade or so. At this point it seems likely that the place of the best human writers is probably safe, but for how long? Time will tell.

    Source: ExtremeTech.com

    • Facebook
    • Twitter
    • Flipboard
    • LinkedIn
    7 comments
    EddieG
    The value of this program to the human race is nil. The potential harm to our communication skills is clear.
    PhilParker
    Eddie,
    The article above is rather dated in terms of it covering recent developments. The following may be of interest, wrt your comment on hummanity:
    http://gulfnews.com/news/gulf/uae/education/campus-in-abu-dhabi-helps-make-farming-easier-with-new-radio-technology-1.1041606
    Thomas Torpey
    I fail to see how "self-organizing information" would be anything but a benefit. Ideologically it may be correct to state that the basic skills used are being "obsoleted" but consider the advantage regarding the availability of organized information. How would the recent election have gone differently if voters had access to organized, summarized and comprehensive information ready for an "intel-briefing." As to the potential danger; lack of the ability to build a cellphone should not constitute justification to deny its availability, or the validity of the individual using it or how effective that is. Electricity is not evil, electrocution is, and that is an intent.
    Dave B13
    How long before the algorithm is found plagiarizing Wikipedia?
    Синиша Ђурић
    I see great potential in this. I wonder if the author of the algorithm considered possible applications for government institutions, military or private companies? For instance military style of writing is fairly simple and predictable, the same can be said for government offices etc. It would save a lot of time and money. I imagine something like this as a part of MS Office in the future.
    Jean Lamb
    Romance novels? Really? People have thought that way before, only to discover that the editors are human and can tell the difference. Readers can tell, too, or why they have their favorite human authors. There are a large number of subgenres in this field, and even Harlequin, with its rather emphatic set of guidelines, has different lines that they publish. I suspect that any cookie-cutter romances will find some readers, but few good ratings.
    kufu
    So basically he invented a spam-bot to get hundreds of thousands of publications on the Amazon Kindle store and other eBook stores to rake in the money.
    People have been doing this on the internet with auto-generated blogs that have lots of embedded ads since 2000. Basically they give it a keyword, the software searches the internet and finds lots of relevant content and uses some algorithm to generate a new blog site with say 100 randomly generated pages on the topic.
    These blogs offer zero value however. You can usually spot them from reading a single paragraph. It just pollutes the internet. Thankfully Google and others have gotten pretty good and filtering them out.
    Seems like the same thing is going to happen to ebook stores.