Iman M Mahfouz
A Computer-assisted Analysis of Political Speeches: Morsi vs. Obama
Computer-assisted Text Analysis (CATA) overcomes many of the limitations of traditional text analysis methods it reduces labor intensity, imposes rigor and discipline and handles complex data manipulations. Recent advances in research tools for the systematic analysis of textual data are enabling exciting new research throughout the social sciences. This paper applies CATA techniques and statistical analysis to speeches of presidents Morsi and Obama, former Egyptian and US presidents respectively. An unsupervised Structural Topic Model (STM) approach is applied to a sample of the political speeches of the two presidents on parallel occasions in order to examine the lexical choices of both presidents in an attempt to find out how they allocate attention to a number of Selected topics, including the country, people, religion, freedom and the future, as well as the relationships between these themes. A comparison is drawn between the speeches of the two presidents using the parameters of frequency of occurrence, comparative analysis, co-occurrence analysis and the effect of the occasion. The identified terms and their use in context suggest significant differences between the two speakers in their choice of words, which may reflect different background, interests and way of thinking. The study also attempts to shed some light on how far computer-assisted text analysis can be applied to political speeches. The study concludes with some recommendations for further research.