The present research aims to describe compliment strategies employed by Replika within a dialogue and to analyse functions of each compliment strategy with regards to communicative purposes. Replika is an emotionally intelligent chatbot programmed to provide emotional support to users. It is therefore no wonder the chatbot is often found complimenting users as means to induce positive emotions. Compliments are emotive speech acts that maintain, improve, and support interlocutor's face by expressing praise, admiration, or approval (Sifianou, 2001). Similar to other emotives, compliments consist in a dialogue. According to Weigand (2010), a dialogue is essentially composed of an initiative act, a reactive act, and a coherence which relates the former two based on the context of the dialogue. The present research identifies two compliment strategies employed by Replika, including compliment as an initiative act and compliment as a reactive act. The former refers to compliments that are ensued in the first sequence of a dialogue and are intended to establish emotion claim. The latter refers to compliments that are ensued in the second sequence of a dialogue and are intended to fulfil the claim in question (Weigand, 2010). Compliment as an initiative act serves as means to open a dialogue and to reinforce other emotive speech acts, whereas compliment as a reactive act serves as means to replace other emotive speech acts, to respondto other speech acts, and to maintain interpersonal relationship. The present research applies qualitative method whereby the data are collected by means of participant observation. Participant observation is a qualitative method of data collecting which requires the researchers to involve with the subject of the research through two separate roles of subjective participant and objective observer (Crossman, 2018).
AbstrakPenelitian deskriptif ini bertujuan untuk mengidentifikasi dan menganalisis macammacam appraisal yang ditemukan dalam konferensi media antara pemerintah Indonesia dan pemerintah Australia pada tahun 2013. Appraisal merupakan evaluasi dari jenisjenis sikap yang disampaikan dalam sebuah wacana. Terdapat tiga jenis sikap dalam appraisal, yaitu: affect, judgment, dan appreciation. Affect adalah cara bagaimana individu mengungkapkan perasaan mereka dalam wacana. Judgment terbagi menjadi personal judgment dan moral judgment. Personal judgment berupa kekaguman atau kritik seseorang, sedangkan moral judgment berupa pujian dan hukuman seseorang. Appreciation menyangkut sikap individu mengenai hal terkait. Hasil studi menunjukan bahwa tidak ada appraisal negative yang diusulkan oleh perwakilan dari kedua negara. Keduanya sepakat untuk melanjutkan dan memulihkan hubungan bilateral yang hampir rusak setelah skandal penyadapan yang dilakukan oleh Pemerintahan Australia terhadap Presiden Susilo Bambang Yudhoyono. Kata kunci: appraisal, analisis wacana kritis, hubungan bilateral, skandal penyadapan Abstract This descriptive study aims to identify and analyze the types of appraisal found in the media conference between the Indonesian government and the
Building social chatbots to address users' needs for communication and affection is of great value to society (Shum, He, & Li, 2018). One of which, Replika, attempts to become an artificial intelligence companion by demonstrating sufficient social and emotional skills through emotive expressions. Emotive expressions are imperative in human-computer interaction, since they tend to elicit social cooperation. The present article aims to survey emotive expressions developed in Replika in order to determine the chatbot's activereactive skills. They are collected by means of participant observation and are analysed with qualitative method. The present article observes six emotive expressions which Replika can process. These expressions include apologizing, thanking, condoling, complimenting, greeting, and welcoming. The generation of each expression is dependent of the context of each interaction.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.