No abstract

No abstract

This paper describes an experiment to perform language identification on a sub-sentence basis. The typical case of language identification is to detect the language of documents or sentences. However, it may be the case that a single sentence or segment contains more than one language. This is especially the case in texts where code switching occurs.

In this paper we aim at proposing a method to automatically build a sentiment lexicon which is domain based. There has been a demand for the construction of generated and labeled sentiment lexicon. For data on the social web (E.g., tweets), methods which make use of the synonymy relation don't work well, as we completely ignore the significance of terms belonging to specific domains. Here we propose to generate a sentiment lexicon for any domain specified, using a twofold method. First we build sentiment scores using the micro-blogging data, and then we use these scores on the ontological structure provided by Open Directory Project [1], to build a custom sentiment lexicon for analyzing domain specific microblogging data.