Logo des Repositoriums

Auflistung nach Autor:in "Dykes, Natalie"

1 - 2 von 2
  • Zeitschriftenartikel
    Argument parsing via corpus queries
    (it - Information Technology: Vol. 63, No. 1, 2021) Dykes, Natalie; Evert, Stefan; Göttlinger, Merlin; Heinrich, Philipp; Schröder, Lutz
    We present an approach to extracting arguments from social media, exemplified by a case study on a large corpus of Twitter messages collected under the #Brexit hashtag during the run-up to the referendum in 2016. Our method is based on constructing dedicated corpus queries that capture predefined argumentation patterns following standard Walton-style argumentation schemes. Query matches are transformed directly into logical patterns, i. e. formulae with placeholders in a general form of modal logic. We prioritize precision over recall, exploiting the fact that the sheer size of the corpus still delivers substantial numbers of matches for all patterns, and with the goal of eventually gaining an overview of widely-used arguments and argumentation schemes. We evaluate our approach in terms of recall on a manually annotated gold standard of 1000 randomly selected tweets for three selected high-frequency patterns. We also estimate precision by manual inspection of query matches in the entire corpus. Both evaluations are accompanied by an analysis of inter-annotator agreement between three independent judges.
  • Zeitschriftenartikel
    Reconstructing Arguments from Noisy Text
    (Datenbank-Spektrum: Vol. 20, No. 2, 2020) Dykes, Natalie; Evert, Stefan; Göttlinger, Merlin; Heinrich, Philipp; Schröder, Lutz
    Social media are of paramount importance to public discourse. RANT aims to contribute methods and formalisms for extracting, representing, and processing arguments from noisy text found in social media discussions, using a large corpus of pre-referendum Brexit tweets as a running case study. We identify recurring linguistic argumentation patterns in a corpus-linguistic analysis and formulate corresponding corpus queries to extract arguments automatically. Given the huge amount of social media data available, our approach aims at high precision at the possible price of low recall. Argumentation patterns are directly associated with logical patterns in a dedicated formalism and accordingly, individual arguments are directly parsed as logical formulae. The logical formalism for argument representation features a broad range of modalities capturing real-life modes of expression. We cast this formalism as a family of instance logics in the generic framework of coalgebraic logic and complement it by a flexible framework to represent relationships between arguments; including standard relations like attack and support but also relations extracted from metadata. Some relations are inferred from the logical content of individual arguments. We are in the process of developing suitable generalizations of various extension semantics for argumentation frameworks combined with corresponding algorithmic methods to allow for the automated retrieval of large-scale argumentative positions.