This paper presents an overview of past papers published at the CBMS symposiums from a content analysis point of view. A simple, yet effective word counting using Harvard Psycho-Social dictionary was used to estimate different aspects of sentiment that can be present even in scientific papers. Using simple statistics we uncover some of the very interesting trends in the last five CBMS symposiums. Additional to pure statistics we used some of the most advanced classification techniques to see if there are any significant differences in psycho-social texture of the accepted papers. It was also shown that building machine learning models on this kind of data can result in some very interesting generalizations of the underlying data.