ON THE UTILITY OF CONTENT-ANALYSIS IN AUTHOR ATTRIBUTION - THE FEDERALIST

In studies of author attribution, measurement of differential use of f unction words is the most common procedure, though lexical statistics are often used. Content analysis has seldom been employed. We compare the success of lexical statistics, content analysis, and function word s in classifying the 12 disputed Federalist papers. Of course, Mostell er and Wallace (1964) have presented overwhelming evidence that all 12 were by James Madison rather than by Alexander Hamilton. Our purpose is not to challenge these attributions but rather to use The Federalis t as a test case. We found lexical statistics to be of no use in class ifying the disputed papers. Using both classical canonical discriminan t analysis and a neural-network approach, content analytic measures - the Harvard III Psychosociological Dictionary and semantic differentia l indices - were found to be successful at attributing most of the dis puted papers to Madison. However, a function-word approach is more suc cessful. We argue that content analysis can be useful in cases where t he function-word approach does not yield compelling conclusions and, p erhaps, in preliminary screening in cases where there are a large numb er of possible authors.