Search

We describe the Open University team's submission to the 2011 i2b2/VA/Cincinnati Medical Natural Language Processing Challenge, Track 2 Shared Task for sentiment analysis in suicide notes. This Shared Task focused on the development of automatic systems that identify, at the sentence level, affective text of 15 specific emotions from suicide notes. We propose a hybrid model that incorporates a number of natural language processing techniques, including lexicon-based keyword spotting, CRF-based emotion cue identification, and machine learning-based emotion classification. The results generated by different techniques are integrated using different vote-based merging strategies. The automated system performed well against the manually-annotated gold standard, and achieved encouraging results with a micro-averaged F-measure score of 61.39% in textual emotion recognition, which was ranked 1st place out of 24 participant teams in this challenge. The results demonstrate that effective emotion recognition by an automated system is possible when a large annotated corpus is available.

This paper discusses how we intend to take forward the vision of a Bibliography of Life in the ViBRANT project. The underlying principle of the Bibliography is to provide taxonomists and others with a freely accessible bibliography covering the whole of life. Such a bibliography has been achieved for specific study areas within taxonomy, but not for "life" as a whole.The creation of such a comprehensive tool has been hindered by various social and technical issues. The social concerns focus on the willingness of users to contribute to the Bibliography. The technical concerns relate to the architecture required to deliver the Bibliography. These issues are discussed in the paper and approaches to addressing them within the ViBRANT project are described, to demonstrate how we can now seriously consider building a Bibliography of Life. We are particularly interested in the potential of the resulting tool to improve the quality of bibliographic references. Through analysing the large number of references in the Bibliography we will be able to add metadata by resolving known issues such as geographical name variations. This should result in a tool that will assist taxonomists in two ways. Firstly, it will be easier for them to discover relevant literature, especially pre-digital literature; and secondly, it will be easier for them to identify the canonical form for a citationThe paper also covers related issues relevant to building the tool in ViBRANT, including implementation and copyright, with suggestions as to how we could address them.