Skip to main content

Web, Social Media and Enterprise Data Extraction, Mining, Search and Integration

J Hong

Our research on data extraction, mining, search and integration is conducted with research problems that arise in three main application areas: World-Wide Web, social media and enterprises (corporate Intranets). The overall goal of this research is to develop algorithms and tools that extract structured data from unstructured and semi-structured data sources, discover knowledge from these sources, retrieve data efficiently from these sources, integrate data from multiple data sources, and apply these algorithms and tools to solve application challenges in the areas of World-Wide Web, social media and enterprises.

Specific areas of interest include:

  • Deep web data extraction, crawling, search and integration
  • Text extraction, text and web mining
  • Conversational recommendation systems
  • Enterprise data extraction and semantic search
  • Social media mining, including sentiment analysis and opinion mining
This research has a variety of applications. The Web, social media and corporate Intranets contain massive amount of data. Companies or organisations have a large number of pre-existing, autonomous and independently created data repositories. Scientists produce a large volume of scientific and experimental data. Computerisation of businesses, services, governments and commerce creates the big data problem. Data extraction, mining, search and integration lies in the heart of all these applications.