Text-Mining the Web

Recently, I worked with Cécile Alduy, Professor of French, and SUL's Nicholas Taylor and Sarah Sussman to use SUL's Web Archiving Service to generate a corpus of French political websites that we text-mine. The results informed Alduy's latest book, Ce qu'ils disent vraiment: Les politiques pris aux mots. Now, I've written up the details of this process, which you can read on my website.