ABSTRACT

Th e human body of knowledge has been exponentially increasing since humanity fi rst set foot on earth. Along with the growth in knowledge comes the diffi culty to master it all, yet this obstacle has not caused any major problems for pushing the boundaries of knowledge even further. Th is is due to the growth of methods that help individuals learn only what is most relevant to their immediate interests. Text classifi cation (TC) and information retrieval (IR) methods are of great importance for the information retrieval tasks as they help us search the complete body of knowledge available in the way we think will suit us most. In this chapter we briefl y mention what was done in the past to help people fi nd this material, introduce some heuristics that people use on a daily basis for such purposes, and fi nally discuss the mathematical models that are used to help with TC and IR.