“…In a second step, we present the results of investigating how well the natural language descriptions match to the seller-generated content, to the product reviews given by other buyers, and to the facets currently available in popular product search systems. The complete dataset of the user study, including the segmentations and annotated vagueness scores, is publicly available 6 . Figure 1 shows the histogram of annotated vagueness of all 132 user-generated product descriptions.…”
Section: Resultsmentioning
confidence: 99%
“…Voice assistants have been evaluated in many scenarios [6,7,32,39], highlighting the potential for conversational interaction, but also showing existing challenges. Cambre et al [6] employed a voice assistant in a laboratory setting, noting the challenge of the versatile natural language vocabulary. In their use case, the system was unable to understand technical terms used during laboratory work.…”
Section: Natural Language In Voice Interactionsmentioning
confidence: 99%
“…In their use case, the system was unable to understand technical terms used during laboratory work. Missing context is also a problem often described in literature [6,23,32]. To date, interacting with voice assistants is mostly restricted to simple commands and implemented "skills".…”
Section: Natural Language In Voice Interactionsmentioning
confidence: 99%
“…The domains show a weak significant difference in means (p = .043), with the laptop descriptions being rated more vague (M = 5.10, SD = 2.16) than the jacket descriptions (M = 4.48, SD 6 https://git.gesis.org/papenmaa/dis20_ usersearchintentformulation Figure 1. Histogram of vagueness annotations for all 132 user-generated descriptions.…”
Section: Vagueness In User Descriptionsmentioning
confidence: 99%
“…Likewise, voice assistants such as Siri, Alexa, or Cortana are dependent on understanding and interacting with natural language. Applications of voice assistants in laboratory assistants [6] or Smart Homes [7,34] show the usefulness of voice as an input modality, but, at the same time, highlight existing problems: Conversation techniques are not yet sophisticated enough to elicit long-term usage [7] and natural language has a great variance in vocabulary [6]. Already in 1987, Furnas et al [11] noted the "vocabulary problem": The natural language of users is not equal to the controlled language used to index information in search systems.…”
With the rise of voice assistants and an increase in mobile search usage, natural language has become an important query language. So far, most of the current systems are not able to process these queries because of the vagueness and ambiguity in natural language. Users have adapted their query formulation to what they think the search engine is capable of, which adds to their cognitive burden. With our research, we contribute to the design of interactive search systems by investigating the genuine information need in a product search scenario. In a crowd-sourcing experiment, we collected 132 information needs in natural language. We examine the vagueness of the formulations and their match to retailer-generated content and user-generated product reviews. Our findings reveal high variance on the level of vagueness and the potential of user reviews as a source for supporting users with rather vague search intents.
“…In a second step, we present the results of investigating how well the natural language descriptions match to the seller-generated content, to the product reviews given by other buyers, and to the facets currently available in popular product search systems. The complete dataset of the user study, including the segmentations and annotated vagueness scores, is publicly available 6 . Figure 1 shows the histogram of annotated vagueness of all 132 user-generated product descriptions.…”
Section: Resultsmentioning
confidence: 99%
“…Voice assistants have been evaluated in many scenarios [6,7,32,39], highlighting the potential for conversational interaction, but also showing existing challenges. Cambre et al [6] employed a voice assistant in a laboratory setting, noting the challenge of the versatile natural language vocabulary. In their use case, the system was unable to understand technical terms used during laboratory work.…”
Section: Natural Language In Voice Interactionsmentioning
confidence: 99%
“…In their use case, the system was unable to understand technical terms used during laboratory work. Missing context is also a problem often described in literature [6,23,32]. To date, interacting with voice assistants is mostly restricted to simple commands and implemented "skills".…”
Section: Natural Language In Voice Interactionsmentioning
confidence: 99%
“…The domains show a weak significant difference in means (p = .043), with the laptop descriptions being rated more vague (M = 5.10, SD = 2.16) than the jacket descriptions (M = 4.48, SD 6 https://git.gesis.org/papenmaa/dis20_ usersearchintentformulation Figure 1. Histogram of vagueness annotations for all 132 user-generated descriptions.…”
Section: Vagueness In User Descriptionsmentioning
confidence: 99%
“…Likewise, voice assistants such as Siri, Alexa, or Cortana are dependent on understanding and interacting with natural language. Applications of voice assistants in laboratory assistants [6] or Smart Homes [7,34] show the usefulness of voice as an input modality, but, at the same time, highlight existing problems: Conversation techniques are not yet sophisticated enough to elicit long-term usage [7] and natural language has a great variance in vocabulary [6]. Already in 1987, Furnas et al [11] noted the "vocabulary problem": The natural language of users is not equal to the controlled language used to index information in search systems.…”
With the rise of voice assistants and an increase in mobile search usage, natural language has become an important query language. So far, most of the current systems are not able to process these queries because of the vagueness and ambiguity in natural language. Users have adapted their query formulation to what they think the search engine is capable of, which adds to their cognitive burden. With our research, we contribute to the design of interactive search systems by investigating the genuine information need in a product search scenario. In a crowd-sourcing experiment, we collected 132 information needs in natural language. We examine the vagueness of the formulations and their match to retailer-generated content and user-generated product reviews. Our findings reveal high variance on the level of vagueness and the potential of user reviews as a source for supporting users with rather vague search intents.
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.