In this study, we address the interesting task of classifying historical texts by their assumed period of writing. This task is useful in digital humanity studies where many texts have unidentified publication dates. For years, the typical approach for temporal text classification was supervised using machine-learning algorithms. These algorithms require careful feature engineering and considerable domain expertise to design a feature extractor to transform the raw text into a feature vector from which the classifier could learn to classify any unseen valid input. Recently, deep learning has produced extremely promising results for various tasks in natural language processing (NLP). The primary advantage of deep learning is that human engineers did not design the feature layers, but the features were extrapolated from data with a general-purpose learning procedure. We investigated deep learning models for period classification of historical texts. We compared three common models: paragraph vectors, convolutional neural networks (CNN), and recurrent neural networks (RNN). We demonstrate that the CNN and RNN models outperformed the paragraph vector model and supervised machine-learning algorithms. In addition, we constructed word embeddings for each time period and analyzed semantic changes of word meanings over time.