Comments on: Be careful with dictionary-based text analysis http://brenocon.com/blog/2011/10/be-careful-with-dictionary-based-text-analysis/ cognition, language, social systems; statistics, visualization, computation Tue, 25 Nov 2025 13:11:20 +0000 hourly 1 By: kisho http://brenocon.com/blog/2011/10/be-careful-with-dictionary-based-text-analysis/#comment-1895038 kisho Tue, 02 Sep 2014 04:51:19 +0000 http://brenocon.com/blog/?p=1050#comment-1895038 Good article. I am currently writing thesis related to the sentiment analysis using lexical. To be honest I found the fear when working on assessment dictionary. For first step, I do seeking any formal vocabulary in the formal dictionary, if no I’ll look it up in the dictionary of non-formal (slang) – there happens to be a website that makes a collection of slang words according to the language. Third, I’m looking how often and how to use it in our daily conversation. Does 3 steps is enough to determine the value, for case I am the only one coder?

Sorry for my English, thank you.

]]> By: Denzil http://brenocon.com/blog/2011/10/be-careful-with-dictionary-based-text-analysis/#comment-85028 Denzil Wed, 05 Oct 2011 19:08:49 +0000 http://brenocon.com/blog/?p=1050#comment-85028 I am more worried about young scholars using sentiment analysis as a “tool” and reporting sentiments while basing their research on such so called analysis. What’s morer worrying is that they use such dictionary based approaches in an informal content setting like Twitter. One needs to be very careful before such steps are taken.

Also, grnerating domain specific lexicons is a well known and established problem in opinion mining.

]]>