Don't Believe The Hype!

Rough, Daniel; Cowan, Benjamin R.

doi:10.1145/3405755.3406140

Cited by 5 publications

(2 citation statements)

References 7 publications

(8 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A few previous works highlighted the challenges and work practices of building conversational systems. Researchers usually forget this perspective when focusing on "end-user developers" [39], "conversational content curators" [90], and "builders" [62]. Most of the studies published in HCI and conversational user interfaces conferences and journals [1,14,19,51,57] direct their attention to final user challenges and neglect the invisible work of data curators.…”

Section: Teaching Conversational Agentsmentioning

confidence: 99%

“…Other works such as [62] denominate the content curators as CUI builders, affirming that commercial tools claim no need for previous knowledge in programming languages and API integration, and offering suggestions to drive the development of CUI creation tools. Choi et al [18] recognize the challenges of recruiting participants, collecting structured feedback on specific conversational components and platforms, and they propose a curation-tool powered by crowd workers.…”

Section: Teaching Conversational Agentsmentioning

confidence: 99%

See 1 more Smart Citation

Unveiling Practices of Customer Service Content Curators of Conversational Agents

Candello

Pinhanez

Müller

et al. 2022

Proc. ACM Hum.-Comput. Interact.

View full text Add to dashboard Cite

Conversational interfaces require two types of curation: data curation by data science workers and content curation by domain experts. Recent years have seen the possibilities for content curators to instruct conversational machines in the customer service domain (i.e., Machine Teaching). The activities of curating specialized data are time-consuming. These activities have a learning curve for the domain expert, and they rely on collaborators beyond the domain experts, including product owners, technology expert curators, management, marketing, and communication employees. However, recent research has looked at making this task easier for domain experts with a lack of knowledge in the Machine Learning system, and few papers have investigated the work practices and collaborations involved in this role. This paper aims to fill this gap, presenting and unveiling practices extracted from eleven semi-structured interviews and four design workshops with experts in Banking, Technical support, Humans Resources, Telecommunications, and Automotive sectors. First, we investigate the articulation work of the content curators and tech curators in training conversational machines. Second, we inspect the curatorial and collaboration strategies they use, which are not afforded by current conversational platforms. Third, we draw the design implications and possibilities to support individual and collaboration curating practices. We reflect on how those practices rely on self and collaboration with others for curation, trust, and data tracking and ownership.

show abstract