Cover Image
QR Code

MANY FACES OF A CHATBOT: THE USE OF POSITIVE AND NEGATIVE POLITENESS STRATEGIES IN ARGUMENTATIVE COMMUNICATION WITH A CHATBOT.

With the ever-growing development of artificial intelligence, communication and argumentation processes are no longer limited to face-toface and computer-mediated communication with other humans. They now involve communication with machines. This fact has given rise to chatbots, computer programs tr...

Full description

Published in:Journal of Language & Literary Studies / Folia Linguistica & Litteraria no. 49; pp. 158 - 178
Main Author: Ivković, Gordana
Format: Article
Published: Journal of Language & Literary Studies / Folia Linguistica & Litteraria 2024
Subjects:
Artificial intelligence
Politeness theory
Chatbots
Linguistic politeness
Communication
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=183581086&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 183581086
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        18008542
        MSH0
      jtl: Journal of Language & Literary Studies / Folia Linguistica & Litteraria
      issn: 18008542
      maglogo: N
    pubinfo:
      dt: 2024
      iid: 49
      pid: 63970
      pub: Journal of Language & Literary Studies / Folia Linguistica & Litteraria
    artinfo:
      ui:
        183581086
        10.31902/fll.49.2024.9
      ppf: 158
      ppct: 20
      formats:
      tig:
        atl: MANY FACES OF A CHATBOT: THE USE OF POSITIVE AND NEGATIVE POLITENESS STRATEGIES IN ARGUMENTATIVE COMMUNICATION WITH A CHATBOT.
      aug:
        au: Ivković, Gordana
        affil: Faculty of Philosophy, University of Niš
      su:
        Artificial intelligence
        Politeness theory
        Chatbots
        Linguistic politeness
        Communication
      sug:
        subj:
          Artificial intelligence
          Politeness theory
          Chatbots
          Linguistic politeness
          Communication
      keyword:
        argumentation
        artificial intelligence
        chatbot
        politeness theory
        positive and negative politeness strategies
        četbot
        argumentacija
        pozitivne i negativne strategije učtivosti
        teorija učtivosti
        veštačka inteligencija
      ab:
        With the ever-growing development of artificial intelligence, communication and argumentation processes are no longer limited to face-toface and computer-mediated communication with other humans. They now involve communication with machines. This fact has given rise to chatbots, computer programs trained to produce human-like communication through the use of highly specified algorithms. The aim of this study was to determine whether a chatbot has been trained in accordance with positive and negative face wants, which were a part of the politeness theory introduced by Brown and Levinson. More specifically, the aim was to determine whether positive and negative politeness strategies would affect the quality of answers a chatbot produces. The chatbot was asked 10 questions in total, grouped into five sets of questions that prompted answers followed by argumentation. Each set contained two questions on the same topic, one question asked utilizing positive politeness strategies, and the other question asked using negative politeness strategies. The results show that 1) there were no significant differences in the answers given to the two types of questions, 2) the chatbot did not select only one type of politeness strategies, 3) more elaborate answers to one of the questions from the sets were produced in relation to the topic of that question rather than the politeness strategies. The most dominant argumentation structure is based on coordinative arguments, with causal schemes appearing most frequently. All of the answers are acceptable in the sense that they give coherent arguments for a standpoint, except for one answer where the opposite standpoints were provided.
        Sa konstantnim razvojem veštačke inteligencije, procesi komunikacije i argumentacije više nisu ograničeni na komunikaciju između ljudskih bića, uživo, ili uz pomoć računara. Oni sada uključuju i komunikaciju sa mašinama. Ova činjenica dovela je do razvoja četbotova, računarskih programa obučenih da komuniciraju na način sličan ljudima kroz upotrebu visoko specifikovanih algoritama. Cilj ovog istraživanja bio je utvrditi da li je četbot obučen u skladu sa pozitivnim i negativnim strategijama učtivosti, koje, kao deo teorije učtivosti, prvi put spominju Braun i Levinson. Preciznije, cilj je bio utvrditi da li ove strategije utiču na kvalitet odgovora koje četbot daje. Četbotu je postavljeno 10 pitanja ukupno, podeljenih u 5 grupa pitanja koja su zahtevala odgovore praćene argumentacijom. Svaka grupa brojala je po dva pitanja na istu temu, jedno sastavljeno uz pomoć pozitivnih strategija učtivosti, a drugo uz pomoć negativnih strategija. Rezultati pokazuju da 1) nema značajnih razlika u odgovorima na dve vrste pitanja, 2) četbot se nije opredelio za jednu vrstu strategija učtivosti, 3) opširniji odgovori na jedno pitanje iz grupe dati su na osnovu teme kojom se pitanje bavi, a ne na osnovu strategija učtivosti. Najdominantnija struktura argumentacije zasniva se na koordiniranim argumentima, dok je kauzalna shema najčešća. Svi odgovori četbota su prihvatljivi u smislu da daju koherentne argumente za određeno stanovište, sem jednog odgovora u kome su data suprotstavljena stanovišta.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      dt:
        @attributes:
          year: 2024
    holdings:
      @attributes:
        islocal: N