[{"data":1,"prerenderedAt":292},["ShallowReactive",2],{"project-13474943":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":10,"maker":11,"posted_at":12,"year":13,"points":14,"comments":15,"rank_in_year":16,"shown_in_year":17,"top":18,"tier":19,"category":20,"subcategory":21,"format":22,"keywords":23,"reception":27,"sentiment":28,"stance_mix":29,"scored_comments":34,"aspects":35,"strip":41,"post_text":43,"what":44,"said":75,"maker_in_thread":176,"shape":186,"grid":189,"attempts":254,"same_week":255,"maker_shows":40,"maker_hidden":284,"reader_version":285,"card":286},"13474943","h10","Realtime Hacker News Summarization Using Machine Learning","title","Show HN: Realtime Hacker News Summarization Using Machine Learning","http:\u002F\u002Fhn10.org\u002Findex.html","hn10.org","bexp",1485288222,2017,138,29,287,2242,13,"notable","ai","text summarization","web_app",[24,25,21,26],"hacker news summarizer","nltk","machine learning","curious",-0.075,{"positive":30,"neutral":31,"mixed":32,"critical":33},2,16,0,4,22,{"execution":36,"idea":38,"docs":39},{"positive":32,"critical":37},3,{"positive":30,"critical":32},{"positive":32,"critical":40},1,[37,32,37,37,42,37,37,42,37,32,40,40,32,37,32,37,37,37,37,37,32,40,32,37,37,32,37,40,37],5,null,{"problem":45,"audience":53,"pricing":43,"motivation":43,"time_to_build":43,"stack":57,"openness":73,"stage":74,"team_size":73},{"value":46,"source":47,"evidence":48},"Skimming high volume Hacker News articles quickly without missing content","commenter",[49],{"id":50,"by":51,"text":52},"13476920","mendeza","The summary seems to pick the most unique sentences, so maybe LexRank? Amazing though, I've been really wanting a way to skim HN articles quicker, since there is so much volume…",{"value":54,"source":47,"evidence":55},"Hacker News readers",[56],{"id":50,"by":51,"text":52},[58,65,69],{"value":59,"source":60,"evidence":61},"Python","maker",[62],{"id":63,"by":11,"text":64},"13475889","I used NLTK in Python http:\u002F\u002Fnltk.org + Twisted for serving HTTP",{"value":66,"source":60,"evidence":67},"NLTK",[68],{"id":63,"by":11,"text":64},{"value":70,"source":60,"evidence":71},"Twisted",[72],{"id":63,"by":11,"text":64},"unknown","launched",{"praise":76,"objections":85,"requests":111,"questions":134,"alternatives":154},[77],{"value":78,"source":47,"evidence":79},"Useful idea for skimming HN articles",[80,81],{"id":50,"by":51,"text":52},{"id":82,"by":83,"text":84},"13477506","spraak","I'm glad that someone made this! Ever since I've known about ML and HN I've wanted to make something like this",[86,97,104],{"value":87,"source":47,"evidence":88},"Summary method unclear and needs explanation",[89,93],{"id":90,"by":91,"text":92},"13474985","alistproducer2","This would really benifit from an explanation of what I'm seeing. can't really upvote it without knowing what's going on....",{"id":94,"by":95,"text":96},"13476242","ostegm","Can you describe a little about how you go from raw text to a summary? Is this supervised learning? If so, what is the training data?",{"value":98,"source":47,"evidence":99},"Some posts missing comment links",[100],{"id":101,"by":102,"text":103},"13481989","alexilliamson","There are still posts with no link to the comments. Seems like it is happening whenever the summary is also missing below the title (currently \"5. Ask HN: Leave job right before…",{"value":105,"source":47,"evidence":106},"Web page throws a JS error on load",[107],{"id":108,"by":109,"text":110},"13476294","singularity2001","js error: \"get top stories error index.html:56:4\"",[112,127],{"value":113,"source":47,"evidence":114},"Publish the source code",[115,119,123],{"id":116,"by":117,"text":118},"13478707","a_c","This. It would be great if we can have the source code alongside with OP's comment on his\u002Fher summarization",{"id":120,"by":121,"text":122},"13480141","apapli","Agree. It would be great to see your source code if at all possible, would be greatly appreciated.",{"id":124,"by":125,"text":126},"13490121","mulrian","Is this open source?",{"value":128,"source":47,"evidence":129},"Link to HN comments for each post",[130],{"id":131,"by":132,"text":133},"13477838","s_ngularity","It would be good if it still included a link to the HN comments for each post",[135,146],{"value":136,"source":47,"evidence":137},"Which summarization algorithm is used",[138,142],{"id":139,"by":140,"text":141},"13476840","xiamx","Got that this is using nltk. Can you comment on which summarization algorithm you are using (TextRank, SumBasic and etc.) What's the motivation towards choosing one algorithm…",{"id":143,"by":144,"text":145},"13475815","brunopedro","What summarization algorithm are you using?",{"value":147,"source":47,"evidence":148},"Is there machine learning or training data involved",[149,150],{"id":94,"by":95,"text":96},{"id":151,"by":152,"text":153},"13483705","amirouche","NLTK has no machine learning algorithm AFAIK",[155,162,169],{"value":156,"source":47,"evidence":157},"newspaper library for text extraction",[158],{"id":159,"by":160,"text":161},"13477815","ecesena","Not sure what do you use to scrape, but I can recommend newspaper to extract text. I contributed a while ago and it was pretty solid. https:\u002F\u002Fgithub.com\u002Fcodelucas\u002Fnewspaper",{"value":163,"source":47,"evidence":164},"Mercury web parser API",[165],{"id":166,"by":167,"text":168},"13475972","jeffehobbs","You could probably get cleaner input for step 1 via the Mercury API [https:\u002F\u002Fmercury.postlight.com\u002Fweb-parser\u002F] — it has a lot of affordances for different kinds of HTML…",{"value":170,"source":47,"evidence":171},"thepul.se news summarizer",[172],{"id":173,"by":174,"text":175},"13502384","travelinreid","https:\u002F\u002Fthepul.se\u002F also uses an algorithm based on nltk to summarize general news. (It also includes a nice speed-reader.)",{"comments":177,"answered":30,"key":178},6,[179,182,183],{"id":180,"text":181},"13477818","thanks will try that",{"id":63,"text":64},{"id":184,"text":185},"13475931","there are couple things here: 1. scrapping web page to get text content 2. use NLTK to proccess text and get summary and keywords 3. wrap it into REST API and serve as web service",{"commenters":187,"max_depth":33,"maker_replies":177,"first_comment_mins":42,"lifespan_hours":188},23,72,[190,192,194,198,200,202,204,205,206,209,210,212,214,215,216,219,220,224,227,231,233,236,238,241,243,247,249,251,253],[159,32,37,191,160,32],"maker\u002Fneutral\u002Fexecution",[180,32,32,193,11,40],"maker\u002Fpositive\u002Fnone",[195,32,37,196,197,32],"13479869","project\u002Fneutral\u002Fnone","sohkamyung",[139,40,37,199,140,32],"maker\u002Fneutral\u002Fidea",[50,40,42,201,51,32],"project\u002Fpositive\u002Fidea",[116,40,37,203,117,32],"maker\u002Fneutral\u002Fdocs",[120,40,37,203,121,32],[82,30,42,201,83,32],[207,37,37,191,208,32],"13475835","acd",[63,37,32,191,11,40],[151,37,40,211,152,32],"maker\u002Fcritical\u002Fexecution",[90,33,40,213,91,32],"project\u002Fcritical\u002Fdocs",[184,33,32,191,11,40],[166,33,37,191,167,32],[217,33,32,218,11,40],"13476121","maker\u002Fneutral\u002Fnone",[94,42,37,191,95,32],[221,177,37,222,223,32],"13479562","project\u002Fneutral\u002Fidea","usgroup",[225,177,37,222,226,32],"13481696","aaronhoffman",[228,229,37,222,230,32],"13477929",7,"earthly10x",[131,232,37,222,132,32],8,[234,232,32,235,11,40],"13478413","maker\u002Fpositive\u002Fexecution",[101,232,40,237,102,32],"project\u002Fcritical\u002Fexecution",[173,239,32,240,174,32],9,"other\u002Fneutral\u002Fnone",[143,242,37,191,144,32],10,[244,245,37,222,246,32],"13475907",11,"Raphmedia",[248,245,32,222,11,40],"13475971",[250,245,37,222,246,32],"13476003",[108,252,40,237,109,32],12,[124,18,37,218,125,32],[],[256,261,266,270,275,280],{"id":257,"name":258,"points":259,"category":260},"13458561","DESTIGOGO",377,"consumer_social",{"id":262,"name":263,"points":264,"category":265},"13485501","Teleconsole",334,"infrastructure",{"id":267,"name":268,"points":269,"category":260},"13483865","Bitesnap",174,{"id":271,"name":272,"points":273,"category":274},"13450554","Krihelinator",142,"dev_tools",{"id":276,"name":277,"points":278,"category":279},"13474229","Datapie",126,"data",{"id":281,"name":282,"points":283,"category":274},"13461100","Cage",119,false,"v2",{"id":287,"name":5,"line":6,"ai":284,"cat":20,"year":13,"points":14,"comments":15,"rec":27,"s":288,"top":18,"kw":289,"maker":11,"domain":10,"tier":19,"attempts":32,"strip":290,"url":9,"mix":291,"praise":78,"objection":87,"sub":21},13474943,-0.07,[24,25,21,26],"30335335301103033333010330313",[30,31,32,33],1794036551951]