Elisabetta Rocchetti and Tommaso Locatelli (both University of Milan) have authored a post on the ISLAB at Università degli Studi di Milano’s Tales from the ISLab blog, “John2Vec, or embedding Dewey’s philosophy.” This post describes using an Artificial Neural Network (ANN), in this case, word2vec, on the massive text corpus of the writings of philosopher John Dewey (1859-1952).
This technique allowed the researchers to identify “how vector operations relate to semantic relations”:
For instance, the nearest embedding to Kant is Hegel; Empiricism is placed next to Rationalism; nature and universe embeddings are next to each other. These examples show that Euclidean distances relate to semantic similarities.
To further demonstrate word2vec potential, we try to extract complex relations using vector operations. By adding the difference between two semantically related terms, such as idealism and Hegel, to another embedding, such as Kant, we obtain the vector associated to rationalism. Equivalently, we are comparing Hegel to Kant to find out which is Kant’s school of thoughts. This experiment demonstrates the possibility of extracting analogies through vector operations involving word2vec’s embeddings .
The authors go on to use Dewey’s writings to examine semantic shift:
Semantic shift is a phenomenon that concern the evolution of a word usage. Indeed, the meaning of a word is not fixed once for all and can change over generations, lifetimes or geographical regions.
In this case, semantic shift was used to track Dewey’s changing thought process over time – for instance, which philosophers he’s referencing at different periods of his life and career – as well as for the change in concepts mentioned in relation to education over time.
As the authors note in their closing paragraph, “Computational natural language processing methods can be of great interest for social sciences such as philosophy: experts in this fields can benefit from these tools and techniques to analyse its history and evolution, automatically extracting relevant concepts and thoughts.” Information workers similarly can use ANN’s like word2vec in their own research, or as part of their toolset when working on collaborative projects with others.