Extracting sentiment from text is a hard semantic problem. We develop a methodology for extracting small investor sentiment from stock message boards. The algorithm comprises different classifier algorithms coupled together by a voting scheme. Accuracy levels are similar to widely used Bayes...

Regression equations between a response variable and candidate explanatory variables are often estimated using a training set of data from closely observed locations but are then applied using covariate data held in a GIS to predict the response variable at locations throughout a region. When...

Empirical research is vital if software engineering technology is to be meaningfully evaluated --- without it only guesses can be made at the competing merits of different approaches. Unfortunately, as this thesis demonstrates, much of existing empirical work contains some kind of weakness...

Bringing transactions to an end constitutes a crucial stage of market activity: the detachment between the counterparties engaged in a trade must be guaranteed. In financial markets, this operation relies on organisational technologies, such as clearinghouses, that can reach a high degree of...

This paper seeks to critique the notion of diffusionism. Design/methodology/approach – The notion of diffusionism provides a general way of understanding innovation and human progress. It is pervasive within IS research and practice. Generically, diffusionism denotes an asymmetrical view of...

Decision trees are a widely used knowledge representation in machine learning. However, one of their main drawbacks is the inherent replication of isomorphic subtrees, as a result of which the produced classifiers might become too large to be comprehensible by the human experts that have to...

Trust management seems a promising approach for dealing with security concerns in collaborative applications in a global computing environment. However, the characteristics of this environment require a move from reliable identification to mechanisms for the recognition of entities. Furthermore,...

How value is created for the customer from e-business is a topic of much concern in academic and practitioner circles. In the light of the dot.com downturn, numerous e-business firms ceased to exist. This paper reports the findings from an ongoing research study on the development and decline of...

When small companies grow, they face a range of strategic managerial challenges. Stage models for small company growth predict that a crisis of control can occur when existing information systems for communication and control are no longer able to cope with increased throughput, nor are they...

The rapid development of collaborative environments over the internet has highlighted new concerns over security and trust in such global computing systems. The global computing infrastructure poses an issue of uncertainty about the potential collaborators. Reaching a trusting decision in such...