[{"data":1,"prerenderedAt":268},["ShallowReactive",2],{"project-1923607":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":28,"sentiment":29,"stance_mix":30,"scored_comments":34,"aspects":35,"strip":42,"post_text":44,"what":45,"said":81,"maker_in_thread":180,"shape":187,"grid":191,"attempts":232,"same_week":233,"maker_shows":41,"maker_hidden":260,"reader_version":261,"card":262},"1923607","Groubal CSI","A Bayesian-Based Sentiment Tracker","title","Show HN: We just launched a Bayesian-Based Sentiment Tracker","http:\u002F\u002Fwww.groubalcsi.com\u002F","groubalcsi.com","spxdcz",1290219142,2010,42,20,41,370,12,"shown","data","sentiment analytics","web_app",[24,25,26,27],"sentiment analysis","brand reputation","bayesian classifier","customer satisfaction","roasted",-0.593,{"positive":31,"neutral":31,"mixed":32,"critical":33},1,0,11,13,{"idea":36,"execution":38,"docs":39,"design":40},{"positive":31,"critical":37},3,{"positive":32,"critical":37},{"positive":32,"critical":31},{"positive":32,"critical":41},4,[31,31,31,31,32,31,32,31,32,31,32,31,31,32,31,37,43,32,31,32],5,null,{"problem":46,"audience":44,"pricing":44,"motivation":56,"time_to_build":44,"stack":60,"openness":79,"stage":80,"team_size":79},{"value":47,"source":48,"evidence":49},"Measures how customers feel about brands from social media posts, shown as a satisfaction or dissatisfaction index.","maker",[50,53],{"id":51,"by":11,"text":52},"1923748","It picks up on any Twitter\u002FFB updates that we can measure a discerning 'sentiment' for, so although it's limited to companies\u002Fbrands at the moment, it could certainly be used for…",{"id":54,"by":11,"text":55},"1923712","Thanks for the feedback. Yeah, certainly the 'high = bad' thing is something we grappled with (and still do). The site is a sister-site to a consumer-complaint\u002Fpetition website…",{"value":57,"source":48,"evidence":58},"Sister site to a consumer-complaint petition site, so focused on who is doing badly.",[59],{"id":54,"by":11,"text":55},[61,67,71,75],{"value":62,"source":48,"evidence":63},"PHP",[64],{"id":65,"by":11,"text":66},"1923683","If anyone's interested, we're using the Google Graph API for all the graphs (the spark lines and the big transparent ones at the top), and the Bayesian stuff is based on the PHP…",{"value":68,"source":48,"evidence":69},"MySQL",[70],{"id":65,"by":11,"text":66},{"value":72,"source":48,"evidence":73},"Google Graph API",[74],{"id":65,"by":11,"text":66},{"value":76,"source":48,"evidence":77},"Naive Bayes classifier",[78],{"id":65,"by":11,"text":66},"unknown","launched",{"praise":82,"objections":91,"requests":138,"questions":159,"alternatives":179},[83],{"value":84,"source":85,"evidence":86},"Ideas for expanding into a general reputation tracker.","commenter",[87],{"id":88,"by":89,"text":90},"1923722","rhizome","I don't know if it's intentional, but I would expand your scope beyond complaints. If your math is good you could have a very nice reputation tracker and analytics package in…",[92,107,114,121,128],{"value":93,"source":85,"evidence":94},"High dissatisfaction = bad scale is counter-intuitive.",[95,99,103],{"id":96,"by":97,"text":98},"1923708","physcab","pretty cool. I would change high meaning bad and low meaning good, unless its a rank out of the total. Its a bit counter-intuitive. Why do you just place an emphasis on…",{"id":100,"by":101,"text":102},"1923861","toast76","Call me crazy, but things going UP is generally good. I don't see how you can logically describe something as having an \"increase in worsening satisfaction\". \"AT&T is ranked 1st…",{"id":104,"by":105,"text":106},"1923735","SkyMarshal","I think you only need to change the wording to clarify it: 'Lowest Satisfaction' => 'Most Disatisfied' or 'Highest Disatisfaction' or 'Most Complaints' 'Customer Satisfaction…",{"value":108,"source":85,"evidence":109},"Sentiment is attached to entities, not whole tweets; method questioned.",[110],{"id":111,"by":112,"text":113},"1924068","random42","This is not how sentiment analysis work (or should work). I worked on something similar (Naive Bayes based sentiment analyzer https:\u002F\u002Fgithub.com\u002Fmohitranka\u002FTwitterSentiment). I…",{"value":115,"source":85,"evidence":116},"Rankings seem skewed; some premium brands rank better than down-market ones.",[117],{"id":118,"by":119,"text":120},"1924176","rayval","Interesting but possibly flawed exercise. It would be good to show the entire set of brands sorted from bottom (i.e., good) to top (i.e. bad). I sorted the data and present here…",{"value":122,"source":85,"evidence":123},"Missing units and uncertainty for the scores.",[124],{"id":125,"by":126,"text":127},"1923788","tel","What are the units of dissatisfaction used throughout the page? How do they map to the y-axis of the dissatisfaction graph? What sense of scale do I need to have to understand…",{"value":129,"source":85,"evidence":130},"Broken links for removed companies, now fixed by maker.",[131,135],{"id":132,"by":133,"text":134},"1923739","acangiano","Just FYI, clicking on a company name that has been removed, leads to a 403 error (e.g., Rogers). Also, I sort of broke the site by passing a non-existing company name (e.g.,…",{"id":136,"by":11,"text":137},"1923749","Thanks so much - I knew I could rely on HN'ers to find these things. I'm hoping the Rogers one is a one-off (we're just adding it this morning), but I'll double check all of…",[139,148,152],{"value":140,"source":85,"evidence":141},"Flip the axis or relabel so high scores read as good, or show both directions.",[142,143,147],{"id":96,"by":97,"text":98},{"id":144,"by":145,"text":146},"1923932","mdda","Amount of dissatisfaction is too mushy IMHO. Just title it \"Crapometer\" or \"Hate-o-meter\". Better yet, just flip the Y-axis. I'd think that it would be easier to get a company to…",{"id":104,"by":105,"text":106},{"value":149,"source":85,"evidence":150},"Show the full brand list sorted from best to worst.",[151],{"id":118,"by":119,"text":120},{"value":153,"source":85,"evidence":154},"Longer time span than one week.",[155],{"id":156,"by":157,"text":158},"1924162","DeusExMachina","Is the time span so short just because of initial lack of data? If not, I think it would be useful to change the span of the graph to more than a week, to understand the long…",[160,164,168],{"value":161,"source":85,"evidence":162},"What are the units of the score and what is a given value?",[163],{"id":125,"by":126,"text":127},{"value":165,"source":85,"evidence":166},"Why is it called Bayesian beyond using Naive Bayes?",[167],{"id":125,"by":126,"text":127},{"value":169,"source":85,"evidence":170},"Why do complaints skew mentions of large companies?",[171,175],{"id":172,"by":173,"text":174},"1924095","jhamburger","Something came to mind that will skew this heavily. People will mention a company by name for mainly one of two reasons, either to complain or to tell people about some cool new…",{"id":176,"by":177,"text":178},"1924096","endtime","Are you sure about that distinction? \"Google builds robotic car\" \"Why Groupon is terrible for merchants\"",[],{"comments":181,"answered":182,"key":183},6,2,[184,185,186],{"id":65,"text":66},{"id":136,"text":137},{"id":54,"text":55},{"commenters":188,"max_depth":41,"maker_replies":181,"first_comment_mins":189,"lifespan_hours":190},14,39,7,[192,194,195,197,199,201,202,204,206,208,209,212,213,214,216,217,221,224,226,230],[100,32,31,193,101,32],"project\u002Fcritical\u002Fidea",[111,31,31,193,112,32],[118,182,31,196,119,32],"project\u002Fcritical\u002Fexecution",[125,37,31,198,126,32],"project\u002Fcritical\u002Fdocs",[65,41,32,200,11,31],"project\u002Fneutral\u002Fexecution",[132,41,31,196,133,32],[136,41,32,203,11,31],"maker\u002Fneutral\u002Fnone",[96,43,31,205,97,32],"project\u002Fcritical\u002Fdesign",[54,43,32,207,11,31],"maker\u002Fneutral\u002Fdesign",[104,43,31,205,105,32],[210,43,32,211,11,31],"1923743","maker\u002Fpositive\u002Fnone",[144,43,31,205,145,32],[172,181,31,193,173,32],[176,181,32,215,177,32],"commenter\u002Fneutral\u002Fnone",[156,190,31,205,157,32],[218,219,37,220,173,32],"1924050",8,"project\u002Fneutral\u002Fdesign",[88,222,43,223,89,32],9,"project\u002Fpositive\u002Fidea",[51,222,32,225,11,31],"maker\u002Fneutral\u002Fidea",[227,228,31,196,229,32],"1923799",10,"rorrr",[231,228,32,196,11,31],"1923805",[],[234,239,244,249,253,257],{"id":235,"name":236,"points":237,"category":238},"1931051","penny-bot",74,"games",{"id":240,"name":241,"points":242,"category":243},"1937949","My side project",24,"productivity",{"id":245,"name":246,"points":247,"category":248},"1922845","instantsprite",22,"dev_tools",{"id":250,"name":241,"points":251,"category":252},"1930100",21,"consumer_social",{"id":254,"name":255,"points":228,"category":256},"1927341","Djangy, Heroku for Django","infrastructure",{"id":258,"name":259,"points":181,"category":252},"1923395","christopherwoodall.com",false,"v2",{"id":263,"name":5,"line":6,"ai":260,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":264,"top":18,"kw":265,"maker":11,"domain":10,"tier":19,"attempts":32,"strip":266,"url":9,"mix":267,"praise":84,"objection":93,"sub":21},1923607,-0.59,[24,25,26,27],"11110101010110135010",[31,31,32,33],1793990868678]