## Abstract We point out that questionβanswering systems differ from other informationβseeking applications, such as search engines, by having a deduction capability, an ability to answer questions by a synthesis of information residing in different parts of its knowledge base. This capability requ
Specialists and synthesists in a question answering community
β Scribed by Rich Gazan
- Publisher
- Wiley (John Wiley & Sons)
- Year
- 2007
- Tongue
- English
- Weight
- 35 KB
- Volume
- 43
- Category
- Article
- ISSN
- 0044-7870
No coin nor oath required. For personal study only.
β¦ Synopsis
Abstract
The most sustainable online communities are those that allow and encourage their users to have a voice in how the community evolves. The proliferation of online communities with collaborative filtering mechanisms, where user feedback is aggregated to shape future interactions, makes it necessary to understand why participants in online communities value the content they do. Building on the concepts of users as specialists and synthesists developed in previous research, this study examines Answerbag, an online question answering community where users rate one another's answers to provide collaborative filtering. In this environment, specialists are operationalized as those who claim expertise in a given topic and answer questions without referencing other sources, and synthesists as those who include one or more references to external sources in their answers. The results of the study suggest that within the Answerbag community as a whole, the answers of synthesists tended to be rated more highly than those of specialists, though answers provided by specialists were rated more highly within certain categories. The consequences of differences in the perceived value of information provided by specialists and synthesists are examined, and avenues for future research are discussed.
π SIMILAR VOLUMES
## Abstract In contrast to traditional information retrieval systems, which return ranked lists of documents that users must manually browse through, a question answering system attempts to directly answer natural language questions posed by the user. Although such systems possess languageβprocessi
## Abstract This panel brings together researchers who focus on Q A sites, those that focus on digital reference, and those who bridge between the two, into what we believe will be a lively discussion.
This paper presents the architecture and functionality of a logic prover designed for question answering. The approach transforms questions and answer passages into logic representations based on syntactic, semantic and contextual information. World knowledge supplements the linguistic, ontological,