Untitled

Cohen, Robin; Allaby, Coralee; Cumbaa, Christian; Fitzgerald, Mark; Ho, Kinson; Hui, Bowen; Latulipe, Celine; Lu, Fenghe; Moussa, Nancy; Pooley, David M.; Qian, Alex; Siddiqi, Saheem

doi:10.1023/a:1008398023083

Cited by 37 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, using open-ended statements as prompts, because repeatedly forcing the user to respond to questions limits their agency. Third, selfdisclosure by the conversational agent, which has been shown to have a reciprocal effect on users (Lee et al, 2020), since sharing unprompted information indicates higher initiative (Cohen et al, 1999).…”

Section: ! " # $mentioning

confidence: 99%

“…Control rules based on dialogue acts have been proposed (Whittaker and Stenton, 1988;Walker and Whittaker, 1990); however they do not account for varying degrees of initiative which are common in social conversations. Addressing this, Cohen et al (1999) defines initiative on a spectrum. For example, a command ("Let's talk about cats") is stronger than a suggestion ("Maybe we should talk about cats").…”

Section: Human-human Conversationmentioning

confidence: 99%

“…Chatbot self-disclosure encourages users to share more about themselves than they would otherwise (Lee et al, 2020). Increasing this behavior increases user control, since sharing information without an explicit prompt is a form of initiative (Cohen et al, 1999). Figure 3's Medium level gives an example of how greater user sharing increases initiative.…”

Section: Mechanisms Of Initiativementioning

confidence: 99%

“…Utterance Length We used utterance length as a metric, since sharing unprompted information demonstrates higher initiative (Cohen et al, 1999). Noun Phrases Some long answers may be noninformative, such as "Uhh I'm not really sure about that," thus we also considered the number of distinct noun phrases in user responses, which we detected using spaCy 3 .…”

Section: Metricsmentioning

confidence: 99%

See 3 more Smart Citations

Effective Social Chatbot Strategies for Increasing User Initiative

Hardy,

Paranjape,

Manning

2021

Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue

View full text Add to dashboard Cite

Many existing chatbots do not effectively support mixed initiative, forcing their users to either respond passively or lead constantly. We seek to improve this experience by introducing new mechanisms to encourage user initiative in social chatbot conversations. Since user initiative in this setting is distinct from initiative in human-human or task-oriented dialogue, we first propose a new definition that accounts for the unique behaviors users take in this context. Drawing from linguistics, we propose three mechanisms to promote user initiative: back-channeling, personal disclosure, and replacing questions with statements. We show that simple automatic metrics of utterance length, number of noun phrases, and diversity of user responses correlate with human judgement of initiative. Finally, we use these metrics to suggest that these strategies do result in statistically significant increases in user initiative, where frequent, but not excessive, back-channeling is the most effective strategy.

show abstract

Section: ! " # $mentioning

confidence: 99%

Section: Human-human Conversationmentioning

confidence: 99%

Section: Mechanisms Of Initiativementioning

confidence: 99%

Section: Metricsmentioning

confidence: 99%

See 2 more Smart Citations

Effective Social Chatbot Strategies for Increasing User Initiative

Hardy,

Paranjape,

Manning

2021

Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue

View full text Add to dashboard Cite

show abstract

“…Mixed-initiative interaction allows participants to contribute their unique strengths towards solving a common goal [5], [10], [38]. The basic idea is that initiative (i.e.…”

Section: Mixed-initiative Interactionmentioning

confidence: 99%

Visual Perception and Mixed-Initiative Interaction for Assisted Visualization Design

Healey

Kocherlakota

Rao

et al. 2008

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

Abstract-This paper describes the integration of perceptual guidelines from human vision with an AI-based mixed-initiative search strategy. The result is a visualization assistant called ViA, a system that collaborates with its users to identify perceptually salient visualizations for large, multidimensional datasets. ViA applies knowledge of low-level human vision to: (1) evaluate the effectiveness of a particular visualization for a given dataset and analysis tasks; and (2) rapidly direct its search towards new visualizations that are most likely to offer improvements over those seen to date. Context, domain expertise, and a high-level understanding of a dataset are critical to identifying effective visualizations. We apply a mixed-initiative strategy that allows ViA and its users to share their different strengths and continually improve ViA's understanding of a user's preferences.We visualize historical weather conditions to compare ViA's search strategy to exhaustive analysis, simulated annealing, and reactive tabu search, and to measure the improvement provided by mixed-initiative interaction. We also visualize intelligent agents competing in a simulated online auction to evaluate ViA's perceptual guidelines. Results from each study are positive, suggesting that ViA can construct high-quality visualizations for a range of real-world datasets.

show abstract