Automated Shortlived Website Detection - A study and evaluative prototype |
Subramaniam Ramasubramanian
|
| Abstract | Counterfeit pharmaceutical products are a big threat to the society not only because of the monetary losses incurred by ineffective drugs but also because of the adverse effects they cause to consumers.
It is becoming increasingly more common for these products to find their way to the customer through websites that are marketed in the open Internet.
We work with key stakeholders from research and industry to develop approaches to solve the three key problems of discovering new websites that sell these products, automatically identifying websites that sell these products and classify them into meaningful groups of websites that can be analysed together.
The project also produced a working prototype tool that is used in order to test these approaches identified and documents/analyse the results produced by the tool.
It was observed that the use of user dictionary based mechanisms to discover, identify and rank these websites demonstrated the capability to produce exceptionally high quality results. |
| Type | Master's thesis [Academic thesis] |
| Year | 2015 |
| Publisher | Technical University of Denmark, Department of Applied Mathematics and Computer Science |
| Address | Richard Petersens Plads, Building 324, DK-2800 Kgs. Lyngby, Denmark, compute@compute.dtu.dk |
| Series | DTU Compute M.Sc.-2015 |
| Note | DTU supervisor: Christian D. Jensen, cdje@dtu.dk, DTU Compute |
| Electronic version(s) | [pdf] |
| Publication link | http://www.compute.dtu.dk/english |
| BibTeX data | [bibtex] |
| IMM Group(s) | Computer Science & Engineering |