7 Dictionary Analysis

One of the simplest forms of quantitative text analysis is dictionary analysis. The idea here is to look at the rate at which keywords appear in a text to classify documents into categories. Also, we can measure the extent to which documents belong to particular categories. As we do so without making any assumptions, dictionary methods present a non-statistical to text analysis. A well-known example is measuring the tone in newspaper articles, speeches, children’s writings, and so on by using sentiment analysis dictionaries. Another example is the measuring of policy content in different documents as illustrated by the Policy Agendas Project dictionary (Albaugh et al., 2013).

Here, we will carry out three such analyses, the first a standard analysis and the other two focusing on sentiment. For the former, we will use political party manifestos, while for the latter we will use movie reviews and Twitter data.

References

Albaugh, Q., Sevenans, J., Soroka, S., & Loewen, P. J. (2013). The Automated Coding of Policy Agendas: A Dictionary-based Approach. 6th Annual Comparative Agendas Conference, Antwerp, Belgium.