The availability of large amounts of data provides new research possibilities across research fields. In particularly, large amounts of text from various time periods, genres, media and authors from different societal groups is captures a wealth of information for humanities scholars and social scientists. Given that most of this information is represented by (natural language) text, it is not surprising that text mining technologies have become increasingly popular in these fields. In this talk, I will address the opportunities as well as the pitfalls of applying text mining technologies for exploring big data.