Implicit Opinion Aspect Clues in Portuguese Texts: Analysis and Categorization

The Dantestocks Corpus: An Analysis of the Distribution of Universal Dependencies-Based Part of Speech Tags

“…To help the experts in this task, an annotation manual was built with specific guidelines for the phenomena that are typical of stock market tweets (see Di Felippo et al (2022)). This supporting material was necessary since the annotation guidance described in the UD literature did not provide strategies for the proper treatment of DANTEStocks lexical idiosyncrasies.…”

“…In Natural Language Processing (NLP), Part-of-Speech (PoS) tagging is one of the first processes applied to input data, being responsible for assigning a proper part-of-speech (or grammatical category) to each word in a text. Such basic information is useful for several NLP tasks and applications, as information extraction (CABRAL et al, 2022) (CHIARA, 2022), semantic parsing (ANCHIÊTA; PARDO, 2022) (SENO et al, 2022) and sentiment analysis (MACHADO et al, 2022), just to cite a few of very recently published state of the art research for Portuguese.…”