Signal detection is a challenging task for regulatory and intelligence agencies. Subject matter experts in those agencies analyze documents, generally containing narrative text in a time bound manner for signals by identification, evaluation and confirmation, leading to follow-up action e.g., recalling a defective product or public advisory for potential flu outbreak. Technical challenges to achieve effective signal detection include mining unstructured data, increasing document collections, and presence of multi-domain vocabulary. Lack of annotation and multi-domain vocabulary makes traditional semantic web mining ineffective. Use of heuristics to enhance bag-of-words text mining to semantic text mining is a novel idea attempted for signal detection in this thesis. A semantic text mining framework using information retrieval and extraction techniques for signal detection is presented as a solution. The framework has been validated by analyzing narrative text in medical device event reports and related documents available to the United States Food and Drug Administration. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]