Information School News

Sally Sanger 21st October 2016 at 2pm, Information School, RC-231 Title:  Alcohol online support groups: the role of discussion forums in constructing users’ understanding of their illness/problem Abstract Problem drinking remains a major issue for UK and other societies, affecting individuals, families and communities. Face-to-face support groups, such as Alcoholics Anonymous, can play a large role in helping individuals recover – yet their online counterparts are under-researched and under-used by the NHS. This study aims to analyse and explore the different ways in which online alcohol support groups can contribute to users’ acquisition and development  of beliefs about problem drinking – what it is, what causes it and how it should be dealt with. The research will analyse user postings in online forums and carry out in-depth semi-structured interviews with users to identify the range of methods (including use of story) employed to achieve these ends. As mos...

Christina Maria Founti   21st October 2016 at 10am, Information School, RC-231   Title: Incorporating prediction error estimates in the evaluation of QSAR models   Abstract: Quantitative Structure-Activity Relationship (QSAR) modelling is a widely accepted, non-testing method for generating data in the chemical industries. Limitations of the method are well understood and often require skillful assessment of the accuracy and reliability of models. However, standard measures of model quality are only based on accuracy. This project investigates methods for QSAR model evaluation that account for reliability by incorporating measurement error in collected data and the estimated error of predictions. The literature review focuses on QSAR methods implementing physicochemical and topological features of molecules, supervised machine learning algorithms and main approaches for obtaining prediction error estimates. Benchmark results of a preliminary modelling experiment are re...