• Title/Summary/Keyword: Conversational Relevance

Search Result 5, Processing Time 0.019 seconds

Consumer Perception of Chatbots and Purchase Intentions: Anthropomorphism and Conversational Relevance

  • Chung, Sooyun Iris;Han, Kwang-Hee
    • International Journal of Advanced Culture Technology
    • /
    • v.10 no.1
    • /
    • pp.211-229
    • /
    • 2022
  • In this study, we aimed to define the effects of anthropomorphism and conversational relevance of chatbots on user experience. In specific, the chatbot designed for this study was an online shopping assistant that recommends items for consumers. Levels of anthropomorphism was manipulated by the name, profile picture, word choices, and emojis, while conversational relevance was adjusted by the depth and accuracy of the recommendation. Three categories of user experience were measured: psychological distance, usability, and purchase intentions. The results implied a significant main effect of conversational relevance on all variables for the high anthropomorphized conditions, while all but psychological distance was significant for low anthropomorphized conditions. Although there was no significant main effect of anthropomorphism observed for the variables, the main effect of anthropomorphism on responsibility was marginally significant for a specific item. The results of this study may function as a guidance for future studies regarding usage of chatbots within a marketing setting.

Language Model Adaptation for Conversational Speech Recognition (대화체 연속음성 인식을 위한 언어모델 적응)

  • Park Young-Hee;Chung Minhwa
    • Proceedings of the KSPS conference
    • /
    • 2003.05a
    • /
    • pp.83-86
    • /
    • 2003
  • This paper presents our style-based language model adaptation for Korean conversational speech recognition. Korean conversational speech is observed various characteristics of content and style such as filled pauses, word omission, and contraction as compared with the written text corpora. For style-based language model adaptation, we report two approaches. Our approaches focus on improving the estimation of domain-dependent n-gram models by relevance weighting out-of-domain text data, where style is represented by n-gram based tf*idf similarity. In addition to relevance weighting, we use disfluencies as predictor to the neighboring words. The best result reduces 6.5% word error rate absolutely and shows that n-gram based relevance weighting reflects style difference greatly and disfluencies are good predictor.

  • PDF

Style-Specific Language Model Adaptation using TF*IDF Similarity for Korean Conversational Speech Recognition

  • Park, Young-Hee;Chung, Min-Hwa
    • The Journal of the Acoustical Society of Korea
    • /
    • v.23 no.2E
    • /
    • pp.51-55
    • /
    • 2004
  • In this paper, we propose a style-specific language model adaptation scheme using n-gram based tf*idf similarity for Korean spontaneous speech recognition. Korean spontaneous speech shows especially different style-specific characteristics such as filled pauses, word omission, and contraction, which are related to function words and depend on preceding or following words. To reflect these style-specific characteristics and overcome insufficient data for training language model, we estimate in-domain dependent n-gram model by relevance weighting of out-of-domain text data according to their n-. gram based tf*idf similarity, in which in-domain language model include disfluency model. Recognition results show that n-gram based tf*idf similarity weighting effectively reflects style difference.

Nurses' Question and Explanation Strategies for Effective Communication with Cancer Patients (암환자와의 효과적인 의사소통을 위한 간호사의 질문 및 설명 전략)

  • Lee, Hwa-Jin
    • Journal of Korean Academy of Fundamentals of Nursing
    • /
    • v.18 no.2
    • /
    • pp.247-257
    • /
    • 2011
  • Purpose: This study was conducted to identify communication principles for nurses in cancer units according to Grice's theory. Method: This study was a secondary analysis of qualitative research using conversational analysis. Results: The principles consisted of four maxims: Quality, quantity, relevance and manner and 14 strategies. For the quality maxim, 'asking what you believe to be true' and 'saying the facts you know' strategies were identified. In the quantity maxim, the strategies were 'asking single questions', 'asking open questions' and 'asking optimistic questions'. In the relevance maxim, 'asking about the same theme' and 'giving relevant explanations' strategies were identified. In manner maxim, the strategies were 'using clear expressions in asking questions', 'asking in an orderly way', 'verifying answers', 'using clear expressions in explanations', 'explaining in an orderly way' and 'verifying understanding'. Conclusion: It is expected that these strategies will help and increase the degree of cooperation for nurses in effectively communication with cancer patients.

Disfluency in Language Development (언어발달 과정에 나타난 비유창성 연구)

  • Kim, Tae-Kyung;Chang, Kyung-Hee
    • MALSORI
    • /
    • no.67
    • /
    • pp.61-77
    • /
    • 2008
  • The purpose of this study is to blow the characteristics of disfluency in childhood. The subjects were 144 normal children at the age of between 3 to 8 years who lived in Seoul. All the subjects provided spontaneous conversational speech samples during free-play interactions with their friends. We investigated the patterns and the frequency of disfluency and its relevance with subject's age, speaking rate and MLU(mean length of utterance). The results of this study can be summarized as follows. (1) There was no difference in the frequency of disfluency with the speaker's age or speaking rate. (2) Interjection was the most frequently occurring pattern of disfluency. (3) Prolongation, revision, interjection increased with age while part-word repetition, single-syllable word repetition, multi-syllable word repetition decreased gradually. (4) A significant effect of MLU on the frequency of disfluencies were demonstrated. The regression analysis has shown that more disfluencies occurred in utterances of children whose MLU is longer.

  • PDF