Knowledge extraction

About: Knowledge extraction is a research topic. Over the lifetime, 20251 publications have been published within this topic receiving 413401 citations.

Witten IH, Frank E: Data Mining: Practical Machine Learning Tools and Techniques 2nd edition

Abstract: In the early 1990s some sectors of the computer science community were developing the idea of data understanding as a discovery-driven, systematic and iterative process. This "data mining" research and development area was expected to take advantage of the expansion and consolidation of machine learning methodologies together with the integration of traditional statistical analysis and database management strategies. The main goal was to identify relevant, interesting and potentially novel informational patterns and relationships in large data sets to support decision making and knowledge discovery. In the mid 1990s developers and users of decision-making support systems in areas such as finance (e.g. credit approval and fraud detection applications), marketing and sales analysis (e.g. shopping patterns and sales prediction) were showing a great deal of enthusiasm about the business value of data mining applications. During the next few years international conferences, journals and books were more frequently reporting advances, tools and applications in other areas such as biomedical informatics, engineering, physics, law enforcement and agriculture. Today data mining is seen as a discipline or paradigm that actively aids in the development of these and other scientific areas (e.g. Web-based computing and systems biology).

Building large knowledge bases by mass collaboration

Abstract: Acquiring knowledge has long been the major bottleneck preventing the rapid spread of AI systems. Manual approaches are slow and costly. Machine-learning approaches have limitations in the depth and breadth of knowledge they can acquire. The spread of the Internet has made possible a third solution: building knowledge bases by mass collaboration, with thousands of volunteers contributing simultaneously. While this approach promises large improvements in the speed and cost of knowledge base development, it can only succeed if the problem of ensuring the quality, relevance and consistency of the knowledge is addressed, if contributors are properly motivated, and if the underlying algorithms scale. In this paper we propose an architecture that meets all these desiderata. It uses first-order probabilistic reasoning techniques to combine potentially inconsistent knowledge sources of varying quality, and it uses machine-learning techniques to estimate the quality of knowledge. We evaluate the approach using a series of synthetic knowledge bases and a pilot study in the domain of printer troubleshooting.

Ontology Based Opinion Mining for Movie Reviews

Abstract: Ontology itself is an explicitly defined reference model of application domains with the purpose of improving information consistency and knowledge sharing. It describes the semantics of a domain in both human-understandable and computer-processable way. Motivated by its success in the area of Information Extraction (IE), we propose an ontology-based approach for opinion mining. In general, opinion mining is quite context-sensitive, and, at a coarser granularity, quite domain dependent. This paper introduces a fine-grain approach for opinion mining, which uses the ontology structure as an essential part of the feature extraction process, by taking account the relations between concepts. The experiment result shows the benefits of exploiting ontology structure to opinion mining.

Knowledge Discovery in Database for Tourist Destinations

Abstract: The knowledge discovery in database (KDD) with data mining is a useful tool for the destination management, and more hospitality enterprises and tourist destinations will adopt it in the future. Destination knowledge management requires a multidisciplinary approach and an understanding of tourism. Research and information technology together are imperative to be successful in KDD and data mining. Since useful knowledge management systems must be timely, the destination knowledge discovery system can be a perpetual prototype requiring frequent updating with emphasis on speed in responses and updating. This article discusses various aspects of KDD including operational issues, applications, and data mining. In addition, a hypothetical example of the KDD is provided using Cheju Island in South Korea.