{"id":7030,"date":"2018-01-24T06:54:14","date_gmt":"2018-01-24T11:54:14","guid":{"rendered":"http:\/\/vweisfeld.com\/?p=7030"},"modified":"2018-01-24T06:54:14","modified_gmt":"2018-01-24T11:54:14","slug":"can-robots-write-science-fiction","status":"publish","type":"post","link":"https:\/\/vweisfeld.com\/?p=7030","title":{"rendered":"Can Robots Write Science Fiction?"},"content":{"rendered":"<div id=\"attachment_7031\" style=\"width: 287px\" class=\"wp-caption alignright\"><img data-recalc-dims=\"1\" loading=\"lazy\" decoding=\"async\" aria-describedby=\"caption-attachment-7031\" class=\" wp-image-7031\" src=\"https:\/\/i0.wp.com\/vweisfeld.com\/wp-content\/uploads\/2018\/01\/pen.jpg?resize=277%2C280\" alt=\"pen, writing\" width=\"277\" height=\"280\" srcset=\"https:\/\/i0.wp.com\/vweisfeld.com\/wp-content\/uploads\/2018\/01\/pen.jpg?w=474&amp;ssl=1 474w, https:\/\/i0.wp.com\/vweisfeld.com\/wp-content\/uploads\/2018\/01\/pen.jpg?resize=148%2C150&amp;ssl=1 148w, https:\/\/i0.wp.com\/vweisfeld.com\/wp-content\/uploads\/2018\/01\/pen.jpg?resize=296%2C300&amp;ssl=1 296w\" sizes=\"auto, (max-width: 277px) 100vw, 277px\" \/><p id=\"caption-attachment-7031\" class=\"wp-caption-text\">photosteve101, creative commons license<\/p><\/div>\n<p>Canadian writer Stephen Marche presented the results of his recent experience with \u201calgorithm-guided\u201d writing in a short story published recently in <em>Wired<\/em> (December 2017). The algorithm was developed by the research team of <a href=\"http:\/\/www.adamhammond.com\/other-publications\/\">Adam Hammond<\/a> and Julian Brooke, who use big data to illuminate linguistic issues. We know automated processes have been writing newspaper stories for some time, so far only <a href=\"https:\/\/www.theguardian.com\/technology\/2015\/jun\/28\/computer-writing-journalism-artificial-intelligence\">basic business and sports stories<\/a>, using a program developed by another Hammond, Kris. But pure creative work, Lit-ra-ture?<\/p>\n<p>In a nutshell, Marche collected 50 science fiction short stories he admires and gave them to the researchers. Their software analyzed the stories for style and structure, then gave Marche information on what they have in common.<\/p>\n<p><span style=\"color: #800000;\"><strong>Could this advice help him write a better story?<\/strong><\/span><\/p>\n<p>The analysts first presented Marche with style guidelines to bring the new story he was writing into closer sync with his 50 favorites. Examples of such general guidelines are:<\/p>\n<ul>\n<li>There have to be four speaking characters<\/li>\n<li>26% of the text has to be dialog<\/li>\n<\/ul>\n<p>From there, the analysts developed 14 very specific rules to govern the new story\u2019s content. The usefulness of the rules, though, depended totally on the 50 stories he selected. One rule encouraged greater use of adverbs and even set a quota for the number of adverbs needed in every 100 words of text. That rule probably reflects that, among the 50 stories, were several from decades ago, when adverbs were less frowned upon by editorial tastemakers. Choosing only contemporary stories would probably eliminate that prescription.<\/p>\n<p>Similarly, another rule limited the amount of dialog that should come from female characters\u2014another artifact of an earlier era, one hopes. This, even though the late Ursula K. LeGuin\u2019s story \u201cVaster than Empires and More Slow\u201d was included and stories written by women divide dialog almost equally between male and female characters. Those by men (at least the ones he close) clearly do not. Marche was limited to 16.1%.<\/p>\n<p><span style=\"color: #800000;\"><strong>What did the algorithm \u201cthink\u201d of his story?<\/strong><\/span><\/p>\n<p>Marche wrote a draft of his story, submitted it to his electronic critique group of one, and began to revise. As he worked on it, the software flagged areas\u2014words even\u2014in red or purple where Marche violated the rules, turning green when he fixed it properly. (Sounds soul-crushing, doesn\u2019t it?) Marche says, \u201cMy number of literary words was apparently too high, so I had to go through the story replacing words like <em>scarlet<\/em> with words like <em>red<\/em>.\u201d<\/p>\n<p>I particularly admire Rule Number Six: \u201cInclude a pivotal scene in which a group of people escape from a building at night at high speed in a high tech vehicle made of metal and glass.\u201d Could authors reverse-engineer these rules to help them avoid clich\u00e9 situations and themes? Would it be possible to violate all of them, consistently? Bring new meaning to the phrase \u201cpurple prose\u201d?<\/p>\n<p>Submitted to two real-life editors, Marche\u2019s story was panned as full of unnecessary detail (those adverbs again) and implausible dialog\u2014I guess because the women didn\u2019t speak\u2014and pegged as \u201cpedestrian\u201d and \u201cnot writerly.\u201d<\/p>\n<p>Marche\u2019s human editor was more upbeat: \u201cThe fact that it\u2019s really not that bad is kind of remarkable.\u201d You can <a href=\"https:\/\/www.wired.com\/2017\/12\/when-an-algorithm-helps-write-science-fiction\/\">read the results here<\/a> and decide for yourself. But the fact the software could be helpful at all has me watching my back!<br \/>\n<a href=\"https:\/\/www.amazon.com\/Literature-Digital-Age-Introduction-Introductions-ebook\/dp\/B018MFKPMW\/ref=as_li_ss_il?ie=UTF8&amp;qid=1516794401&amp;sr=8-12&amp;keywords=Adam+Hammond&amp;linkCode=li3&amp;tag=victoweisf-20&amp;linkId=29a9c73ba100b1570b17edae2505f676\" target=\"_blank\" rel=\"noopener\"><img decoding=\"async\" src=\"\/\/ws-na.amazon-adsystem.com\/widgets\/q?_encoding=UTF8&amp;ASIN=B018MFKPMW&amp;Format=_SL250_&amp;ID=AsinImage&amp;MarketPlace=US&amp;ServiceVersion=20070822&amp;WS=1&amp;tag=victoweisf-20\" border=\"0\" \/><\/a><img loading=\"lazy\" decoding=\"async\" style=\"border: none !important; margin: 0px !important;\" src=\"https:\/\/ir-na.amazon-adsystem.com\/e\/ir?t=victoweisf-20&amp;l=li3&amp;o=1&amp;a=B018MFKPMW\" alt=\"\" width=\"1\" height=\"1\" border=\"0\" \/><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Canadian writer Stephen Marche presented the results of his recent experience with \u201calgorithm-guided\u201d writing in a short story published recently in Wired (December 2017). The algorithm was developed by the research team of Adam Hammond and Julian Brooke, who use &hellip; <a href=\"https:\/\/vweisfeld.com\/?p=7030\">Continue reading <span class=\"meta-nav\">&rarr;<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"jetpack_post_was_ever_published":false,"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"Can Robots Write Science Fiction? - one writer's experience following software's advice (nagging, really)","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[62,40,174,186],"tags":[166,30,416,421,414],"class_list":["post-7030","post","type-post","status-publish","format-standard","hentry","category-authors","category-fiction","category-first-draft-blog","category-technology","tag-creativity","tag-novel","tag-real-life","tag-short-story","tag-writing"],"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"jetpack_shortlink":"https:\/\/wp.me\/p2NkiT-1Po","_links":{"self":[{"href":"https:\/\/vweisfeld.com\/index.php?rest_route=\/wp\/v2\/posts\/7030","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/vweisfeld.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/vweisfeld.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/vweisfeld.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/vweisfeld.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=7030"}],"version-history":[{"count":1,"href":"https:\/\/vweisfeld.com\/index.php?rest_route=\/wp\/v2\/posts\/7030\/revisions"}],"predecessor-version":[{"id":7032,"href":"https:\/\/vweisfeld.com\/index.php?rest_route=\/wp\/v2\/posts\/7030\/revisions\/7032"}],"wp:attachment":[{"href":"https:\/\/vweisfeld.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=7030"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/vweisfeld.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=7030"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/vweisfeld.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=7030"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}