[Corpora-List] (no subject)

Anthony Jappy tony at univ-perp.fr
Wed Oct 22 14:44:01 CEST 2008


I have a colleague who has been manually analyzing texts in order to determine whether they are positive or negative with respect to their central theme. For obvious reasons, he would now like to automate the process.

Does anyone know of any way of determining whether the texts in an electronic corpus are positive or negative with respect to their theme: i.e. given a set of texts on capital punishment, is there any way of determining reasonably accurately whether author A’s contribution can be seen as more positive than author B’s, or whether a given text is positive or downright negative? My only experience in this area is with attempts to replicate with students reported results concerning semantic prosodies, certainly not the most economical way of going about the problem mentioned above.

There may have been a thread on this problem, but I'm afraid I don't recall it.

Any bibliographical references would be gratefully accepted.


**************************************************************************** Tony Jappy

Department of English and North-American Studies, University of Perpignan-Via Domitia, 66860 Perpignan Cedex, France tel : +33 (0)4 68 66 22 76 fax : +33 (0)4 68 66 17 28 e-mail : tony at univ-perp.fr


-- Ce message a été vérifié par MailScanner pour des virus ou des polluriels et rien de suspect n'a été trouvé. CRI UPVD http://www.univ-perp.fr

More information about the Corpora mailing list