Subjective Knowledge Acquisition and Enrichment Powered By Crowdsourcing
This work addresses the gap in knowledge bases for handling subjective queries in areas like Web and mobile search, though it is incremental as it builds on existing crowdsourcing and knowledge base techniques.
The paper tackles the problem of acquiring subjective knowledge, which lacks documented ground truth and relies on dominant opinions, by proposing the CoSKA system that uses crowdsourcing and existing knowledge bases to enrich them with subjective facts, achieving effectiveness verified through experiments on real data.
Knowledge bases (KBs) have attracted increasing attention due to its great success in various areas, such as Web and mobile search.Existing KBs are restricted to objective factual knowledge, such as city population or fruit shape, whereas,subjective knowledge, such as big city, which is commonly mentioned in Web and mobile queries, has been neglected. Subjective knowledge differs from objective knowledge in that it has no documented or observed ground truth. Instead, the truth relies on people's dominant opinion. Thus, we can use the crowdsourcing technique to get opinion from the crowd. In our work, we propose a system, called crowdsourced subjective knowledge acquisition (CoSKA),for subjective knowledge acquisition powered by crowdsourcing and existing KBs. The acquired knowledge can be used to enrich existing KBs in the subjective dimension which bridges the gap between existing objective knowledge and subjective queries.The main challenge of CoSKA is the conflict between large scale knowledge facts and limited crowdsourcing resource. To address this challenge, in this work, we define knowledge inference rules and then select the seed knowledge judiciously for crowdsourcing to maximize the inference power under the resource constraint. Our experimental results on real knowledge base and crowdsourcing platform verify the effectiveness of CoSKA system.