作者: Karl Aberer , Zoltán Miklós , Surender Reddy Yerva
DOI:
关键词:
摘要: Ambiguities in company names are omnipresent. This is not accidental, companies deliberately chose ambiguous brand names, as part of their marketing and branding strategy. procedure leads to new challenges, when it comes finding information about the on Web. paper concerned with task classifying Twitter messages, whether they related a given company: for example, we classify set twitter messages containing keyword apple, message Apple Inc. Our technique essentially an SVM classier, which uses simple representation relevant irrelevant form keywords, grouped specic profiles. We developed construct such classiers previously unseen companies, where no training available, by meta-features classier help general testset. techniques show high accuracy figures over WePS-3 dataset.