@INPROCEEDINGS{EPFL-WORKING-151616,
   abstract    = {Ambiguities in company names are omnipresent. This is
                 not accidental, companies deliberately chose ambiguous
                 brand names, as part of their marketing and branding
                 strategy. This procedure leads to new challenges, when it
                 comes to finding information about the company on the
                 Web. This paper is concerned with the task of classifying
                 Twitter messages, whether they are related to a given
                 company: for example, we classify a set of twitter
                 messages containing a keyword apple, whether a message is
                 related to the company Apple Inc. Our technique is
                 essentially an SVM classier, which uses a simple
                 representation of relevant and irrelevant information in
                 the form of keywords, grouped in specic profiles. We
                 developed a simple technique to construct such classiers
                 for previously unseen companies, where no training set is
                 available, by training the meta-features of the classier
                 with the help of a general testset. Our techniques show
                 high accuracy figures over the WePS-3 dataset.},
   address     = {Padua, Italy},
   affiliation = {EPFL},
   author      = {Yerva, Surender Reddy and Miklós, Zoltán and Aberer, Karl},
   details     = {http://infoscience.epfl.ch/record/151616},
   documenturl = {http://infoscience.epfl.ch/record/151616/files/LSIR_WePS3_Paper.pdf},
   keywords    = {Entity Resolution, Twitter, Online Reputation
                 Management; WePS, Machine Learning, SVM},
   oai-id      = {oai:infoscience.epfl.ch:151616},
   oai-set     = {working; fulltext-public; fulltext},
   pagecount   = {13},
   publisher   = {WePS-3, colocated with CLEF},
   status      = {PUBLISHED},
   submitter   = {169837; 169837},
   title       = {It was easy, when apples and blackberries were only fruits},
   unit        = {LSIR},
   year        = 2010
}