[Corpora-List] Spanish Twitter Lexicon

Sat Dec 17 21:02:23 UTC 2011

Hi,

One quick note regarding the second issue Ralph objected to Eugenio's methodology: it's true that a sample filtered on the basis of a given list of opinion words will show some bias (not necessarily problematic of itself if the bias matches the intended filtering criterion), but from that it does not follow that the sample will *only* contain lexically expressed sentiment: the fact that a sentence contains lexemes with an associated sentiment does not exclude the presence of other expressions of sentiment in the same sentence (e.g. "My iPhone is good but..." or "My iPhone is 'good'", where a positive lexeme co-occurs with a negativity inducing ellipsis and negativity inducing punctuation, respectively).

Best,

Jordi

On Dec 17, 2011, at 8:44 PM, ralf.steinberger at jrc.ec.europa.eu wrote:

> Hello Eugenio,
>  
> I fear that your plans will result in a corpus that is moderately useful.
>  
> If you select and annotate only the positive and negative tweets, you can use the result to learn how to distinguish the positive from the negative, but you will not have any data to learn how to distinguish these subjective tweets from the neutral ones. This latter group is important to recognise as it presumably is the majority class. I cannot imagine how the positive-negative distinction is useful if you do not also distinguish the neutral and the subjective cases.
>  
> Another issue is that – using your planned method – you will end up with a non-realistic set of positive and negative tweets, as they will only be those where sentiment is expressed lexically. Any experimental results based on that biased corpus will not be representative for real-life texts.
>  
> It is much more work to annotate all samples from a random selection of texts or snippets, but I believe that this is what you will eventually need to do.
>  
> Greetings to Jaén,
>  
> Ralf
> European Commission – Joint Research Centre (JRC)
> Ispra, Italy
>  
>  
> From: corpora-bounces at uib.no [mailto:corpora-bounces at uib.no] On Behalf Of Eugenio Martínez Cámara
> Sent: 17 December 2011 20:09
> To: Diana Maynard
> Cc: corpora at uib.no
> Subject: Re: [Corpora-List] Spanish Twitter Lexicon
>  
> Thanks Diana for your response and your paper.
>  
> I explain you what I want to do. I have done several experiments with tweets in Spanish following a machine learning approach, but the problem is I don't have a corpus with a reliable labelling, so I want to build a corpus with a manual labelling. So I've downloaded a set of politic tweets during the last Spanish elections. For the manual labelling process, I want to automatically delete those tweets that aren't opinions. So I'm looking for a Spanish or English word list of opinion words. If a tweet doesn't contain any opinion word I consider that it isn't an opinion tweet. I know that a person can express a politic opinion without using any typical opinion word, but it is a simple heuristic to reduce the set of tweets to be manually labelling.
>  
> Regards.
> 
> Eugenio Martínez Cámara.
> Grupo de Investigación SINAI.
> Departamento de Informática.
> Universidad de Jaén.
> emcamara at ujaen dot es
> 
> 
> 
> 
> El 17 de diciembre de 2011 19:40, Diana Maynard <d.maynard at dcs.shef.ac.uk> escribió:
> Hi Eugenio
> Are you asking for some gazetteer list of opinionated words to determine whether a tweet is opinionated or not? Or are you asking for some method which uses bag-of-words (matching against such a list) in order to compare your tools with.
> If the former, obviously you want to be very careful about using such an approach on its own, because there are lots of words which can convey an opinion or not, depending how they are used.
> 
> I am also working on opinion mining from tweets, for English and German, on political tweets amongst other things. You can see my paper about this for English here:
> 
> D. Maynard and A. Funk. Automatic detection of political opinions in tweets. In Proceedings of MSM 2011: Making Sense of Microposts. Workshop at 8th Extended Semantic Web Conference (ESWC 2011). Heraklion, Greece. June 2011.
> http://gate.ac.uk/sale/eswc11/opinion-mining.pdf
> 
> There is also an extended version currently in press.
> Regards
> Diana
> 
> 
> 
> On 17/12/2011 16:05, Eugenio Martínez Cámara wrote:
> Hi All,
> 
> Currently I'm working in Sentiment Analysis on Twitter. I have done
> several experiments with Spanish Twitter corpus following the Go et al.
> (2009) noisy labels technique, but I want to build a gold standard. So,
> I downloaded a corpus of Spanish tweets in the politic domain. At first,
> I want to erase all non-opinion tweets, so I'm going to delete all
> tweets that not contain any opinion word. So, do you know any Spanish
> opinion bag-of-words (positive/negative)? do you know any English
> opinion bag-of-words (positive/negative)?
> 
> Thanks.
> 
> 
> Eugenio Martínez Cámara.
> SINAI Research Group
> Computer Science Department
> University of Jaén
> emcamara at ujaen dot es
> 
> 
> 
> 
> _______________________________________________
> UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
> Corpora mailing list
> Corpora at uib.no
> http://mailman.uib.no/listinfo/corpora
>  
>  
> _______________________________________________
> UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
> Corpora mailing list
> Corpora at uib.no
> http://mailman.uib.no/listinfo/corpora

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.linguistlist.org/pipermail/corpora/attachments/20111217/252c7e32/attachment.htm>
-------------- next part --------------
_______________________________________________
UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora