Opinion Marks : A Human-Based Computation Approach to Instill Structure into Unstructured Text on the Web Article Swipe
YOU?
·
· 2015
· Open Access
·
Despite recent improvements in computational approaches such asmachine learning, natural language processing, and computationallinguistics, making a computer understand human-generated unstructuredtext still remains a difficult problem to solve. To alleviatethe challenges, we propose an approach called “Opinion Marks,”which enables writers to mark positive and negative aspects of atopic on their own text. In addition, Opinion Marks incorporates anautomatic marking suggestion algorithm to offload a user’s markingeffort. The phrases marked with Opinion Marks can be furtherused to clarify the sentiments of other text in a similar context.We implemented Opinion Marks at a question answering websitehttp://caniask.net. To test the efficacy of Opinion Marks, weconducted a crowdsourced experiment with 144 participants in abetween-subject design under three different conditions: 1) humanmarking only; 2) machine marking only (automatic marking suggestion);and 3) human-machine collaboration (Opinion Marks).This study revealed that Opinion Marks significantly improves thequality of marked phrases and usability of the system.
Related Topics To Compare & Contrast
- Type
- article
- Language
- en
- Landing Page
- http://nbn-resolving.de/urn:nbn:de:bsz:352-0-301049
- http://nbn-resolving.de/urn:nbn:de:bsz:352-0-301049
- OA Status
- green
- Cited By
- 1
- References
- 34
- Related Works
- 20
- OpenAlex ID
- https://openalex.org/W2236337979