Adrian O'Riordan

An intelligent agent for high-precision text filtering

We present here an overview of a research project aimed at reducing information overload for individual computer users. High-precision information filtering software has been developed to disseminate on–line electronic information. While the robustness and scalability of statistical approaches to information retrieval were a major influence on our design, we looked to the AI literature to supply the necessary techniques for the creation of an adaptive system. The system, called INFOrmer, is based on art intelligent agent approach and embodies machine learning, adaptation and relevance feedback techniques in its construction. A weighted graph representation is used for documents, and graph manipulation algorithms are used in the processing.

Multiclass Sentiment Classification of Online Health Forums using Both Domain-independent and Domain-specific Features

Online health-related discussion provides a rich source of information for both informing the public and providing feedback to health professionals to detect trends and inform policy. However, there are few studies that focus on analysing sentiment in medical forum discourse. Online health communities devoted to specific medical conditions and health-related problems support people with similar conditions, enabling them to exchange personal experiences. Analysing sentiment expressed by members of a health community in medical forum discourse can be valuable for identifying a particular aspect of the information space. In this paper, we identify sentiments expressed on online medical forums discussing Lyme disease. There are two goals in our research. First, to identify a set of categories that can represent a comprehensive connotation of emotions expressed in the discussions, while also being adequately distinct for the purposes of machine learning. Second, to identify the sentiments expressed by participants in individual posts. Three types of feature (content-free, content-specific and meta-level) are extracted and inductive learning algorithms utilized to build a feature-based classification model for an automated multi-class classification model. The experimental results demonstrate the effectiveness of our approach.