| Popis: |
Opinion mining and sentiment analysis in social media is a research issue having a great interest in the scientific community. However, before begin this analysis, we are faced with a set of problems. In particular, the problem of the richness of languages and dialects within these media. To address this problem, we propose in this paper an approach of construction and implementation of Syntactic analyzer named ASDA. This tool represents a parser for the Algerian dialect that label the terms of a given corpus. Thus, we construct a labeling table containing for each term its stem, different prefixes and suffixes, allowing us to determine the different grammatical parts a sort of POS tagging. This labeling will serve us later in the semantic processing of the Algerian dialect, like the automatic translation of this dialect or sentiment analysis |
