Please enable JavaScript.

Coggle requires JavaScript to display documents.

Text and Web Analytics (Text Mining (Application area (topic tracking…

- - - - Increase cross selling and up selling by analysing call centre data
    - - Spam filtering and deception detection
    - - For DNA and gene expression analysis
    - - Retrieval of information to answer specific queries
  - - - Depends on definition of term and context used
    - - Eg free form text found in emails and recorded telephone transcripts
    - - Grammar ambiguity
  - - - Based on a user profile and documents, test mining can predict other documents of interest to the user
    - - To save time for the reader
    - - Identification of key phrases and relationships within text by looking for patterns
    - - Identifying the main themes of a document and placing it into a predefined set of categories
    - - Group similar documents together
    - - Connects related documents by identifying their shared concepts
    - - Finding the best answer to a given question through knowledge-driven pattern matching
- - - - Understand business goals
        
        Plausible goals for web-based mining: improve usability of website eg. decreasing the average no. of pages visited by a customer before a purchase transaction
    - - Issue
        
        Differentiate individual user sessions
        
        host addresses are not useful (cos multiple users can access to a site from the same host)
        
        able to differentiate different user sessions
        
        Identify unwanted log file entries
        
        single user page request usually generates multiple log file entries from several types of servers
        
        need to have technique to identify unwanted log file entries
        
        Data transformation
        
        new attributes can be added to user session records to improve prediction of outcome
    - - Techniques:
        --> Association Rule Mining
        --> Unsupervised clustering
      - Session file
        
        Data preparation extracts relevant data from web server logs and create a session file suitable for data mining
    - - Interpret results of a web-based mining session using association rule mining and clustering
        
        Summary statistics of website activities complement the interpretation and evaluation of data mining results
        
        Statistics can be produced by web server log analysers (eg. awstats, webalizer)
    - - Targeted Marketing Communications
        
        set up online advertising promotions
        
        send emails to promote products of likely interest to a selected group of registered customers
        
        group products that are likely to be purchased together
      - Webpage Usability Optimization
        
        adapt the indexing structure of a website (to better reflect the paths followed by typical users)
      - Personalisation of web pages based on user profile
        
        implement strategy to personalize website
        
        force user to register at website
        
        data mining to automate personalization based on actual user behaviour