A procedure for studying online conversational processing using a chat bot

Holtgraves, Thomas; Han, T. L.

doi:10.3758/bf03192855

Cited by 31 publications

(15 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In general, people tend to treat the bot like a human (even when they are told it is a bot). For example, we found no difference in processing topic changes as a function of whether participants believed they were chatting with a bot or with another student (Holtgraves & Han, 2007). This is consistent with the frequently demonstrated tendency for people to anthropomorphize artificial agents (e.g., Brennan, 1997;Isbister & Nass, 2000;Lee & Nass, 2004;Sproull, Subramani, Kiesler, Walker, & Waters, 1996).…”

Section: Conversation Researchsupporting

confidence: 77%

“…The bot used in this experiment (described in detail in Holtgraves & Han, 2007) was an extensive modification of the A.L.I.C.E. bot (http://www.alicebot.org/) developed by Richard Wallace.…”

Section: Methodsmentioning

confidence: 99%

“…This, of course, is standard procedure in psycholinguistic research; examining the online cognitive processes of people who are actually involved in a verbal interaction is extremely difficult. Experiment 4 was an attempt to do this using a bot program that had been developed specifically for examining how participants (rather than observers) process conversation utterances (Holtgraves & Han, 2007).…”

Section: Methodsmentioning

confidence: 99%

“…In short, this bot has the potential to allow for the modeling of many aspects of the pragmatics of language use. The AIML content files were edited extensively in order to change the bot's personality from that of a robot (Alice) to a 21-year-old student at Ball State University (see Holtgraves & Han, 2007).…”

Section: Methodsmentioning

confidence: 99%

See 3 more Smart Citations

Automatic intention recognition in conversation processing☆

Holtgraves

2008

Journal of Memory and Language

Self Cite

View full text Add to dashboard Cite

Section: Conversation Researchsupporting

confidence: 77%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Automatic intention recognition in conversation processing☆

Holtgraves

2008

Journal of Memory and Language

Self Cite

View full text Add to dashboard Cite

“…Este tempo de acesso ao léxico para a leitura de uma palavra depende, dentre outros fatores, das características da língua e é considerado o tempo entre a apresentação do estímulo e o início da resposta (15) e, neste estudo, trata-se da leitura de palavras escritas. É uma medida que tem sido utilizada em estudos sobre os processos envolvidos na compreensão da linguagem (16)(17) , na leitura, no reconhecimento de palavras escritas (18)(19)(20) e na nomeação de figuras (21)(22)(23)(24)(25)(26) .…”

Section: Introductionunclassified

Tempo de latência para a leitura: influência da freqüência da palavra escrita e da escolarização

Stivanin

Scheuer

2007

Rev. soc. bras. fonoaudiol.

View full text Add to dashboard Cite

OBJETIVO: Verificar a influência da freqüência das palavras escritas e da escolarização para o tempo de latência. MÉTODOS: Participaram 74 crianças, de 2ª a 4ª séries de escola pública (m=9,6a), ambos os sexos, sem alterações no desenvolvimento e sem queixas escolares. Em computador, com programa particularmente elaborado para esse estudo, aplicou-se um teste de leitura em voz alta de palavras isoladas, caracterizadas por alta e baixa freqüência, variando em regularidade, extensão e complexidade silábica. RESULTADOS: Os dados mostraram que o tempo de latência foi menor para a leitura de palavras freqüentes e houve interação entre série e tipo de palavra. A correlação negativa entre tempo de latência e acertos foi significante, apenas para palavras de baixa freqüência, na 3ª e 4ª séries. COMCLUSÃO: A freqüência influenciou diferentemente o tempo de latência e a precisão da leitura, quando levadas em consideração as características das palavras e a escolarização.

show abstract

Family health history collected by virtual conversational agents: An empirical study to investigate the efficacy of this approach

Ponathil

Ozkan

Welch

et al. 2020

Journal of Genetic Counseling

View full text Add to dashboard Cite

Family health history (FHx) is one of the simplest and most cost-effective and efficient ways to collect health information that could help diagnose and treat genetic diseases at an early stage. This study evaluated the efficacy of collecting such family health histories through a virtual conversational agent (VCA) interface, a new method for collecting this information. Standard and VCA interfaces for FHx collection were investigated with 50 participants, recruited via email and word of mouth, using a within-subject experimental design with the order of the interfaces randomized and counterbalanced. Interface workload, usability, preference, and satisfaction were assessed using the NASA Task Load Index workload instrument, the IBM Computer System Usability Questionnaire, and a brief questionnaire derived from the Technology Acceptance Model. The researchers also recorded the number of errors and the total task completion time. It was found that the completion times for 2 of the 5 tasks were shorter for the VCA interface than for the standard one, but the overall completion time was longer (17 min 44 s vs. 16 min 51 s, p = .019). We also found the overall workload to be significantly lower (34.32 vs. 42.64, p = .003) for the VCA interface, and usability metrics including overall satisfaction (5.62 vs. 4.72, p < .001), system usefulness (5.76 vs. 4.84, p = .001), information quality (5.43 vs. 4.62, p < .001), and interface quality (5.66 vs. 4.64, p < .001) to be significantly higher for this interface as well. Approximately 3 out of 4 participants preferred the VCA interface to the standard one. Although the overall time taken was slightly longer than with standard interface, the VCA interface was rated significantly better across all other measures and was preferred by the participants. These findings demonstrate the advantages of an innovative VCA interface for collecting FHx, validating the efficacy of using VCAs to collect complex patient-specific data in health care.

show abstract

A procedure for studying online conversational processing using a chat bot

Cited by 31 publications

References 20 publications

Automatic intention recognition in conversation processing☆

Automatic intention recognition in conversation processing☆

Tempo de latência para a leitura: influência da freqüência da palavra escrita e da escolarização

Family health history collected by virtual conversational agents: An empirical study to investigate the efficacy of this approach

Contact Info

Product

Resources

About