# Clustering sequences of sentence embeddings

I have a sequence of events, right now I am not worried about their actual times, just the order. This is a sequence of web page views.

I have modelled my data as the following, where each element represents the category of the web page.

user_sequence = ['A', 'A', 'B', 'C', ...]


Following this I used the code and approach from this paper: Sequence Graph Transform

My question is how could I represent more complex data in my sequences, for example, we have an embedding representing the page content, along with features including the dwell of the user on each page.

So to summarise, the goal is to do process sequences of rich event data in an unsupervised manner.