Txtlab
4 FOLLOWERS
The Txtlab blog reports on the latest research findings and collaborations at our lab. '.txtlab' is a laboratory for cultural analytics at McGill University. We explore the use of computational approaches toward understanding literature and culture in both the past and present. Our aim is to use the tools of data science and machine learning to better understand the foundations of..
Txtlab
2w ago
I have a new piece out in the Journal of Computational Literary Studies that studies the behavior of fictional characters. This paper uses machine learning to provide the first ever large-scale estimates of the distribution of actions of literary characters. Looking at over 15 Million unique character actions in both contemporary and historical fiction, I ..read more
Txtlab
1M ago
This paper of mine was recently published as part of the “Big Picture Workshop” that was part of EMNLP 2023. It marks a continuation of earlier work and also a further effort at consolidating the various goals and tasks that are part of the larger endeavour of using natural language processing to understand human storytelling ..read more
Txtlab
5M ago
Excited to share a new piece with Hao Xu and Eric D. Kolaczyk of McGill that is appearing in this year’s Computational Humanities Workshop Proceedings (CHR). In it we tackle the question of how to model the idea of “narrative revelation.” For us, revelation is question of how information is revealed over narrative time. Narrative ..read more
Txtlab
6M ago
I’ve given a few talks recently on the topic of computational narrative understanding so I thought I would share my slides. As I detail in the slides, we have been focusing on the following areas of research towards understanding narratives ..read more
Txtlab
8M ago
At the end of last semester my department asked me to hold an info session about using GPT in the classroom. I went ahead and prepared this document for them. While it is a fast changing set of issues, I think this is still a good introduction for folks who are just beginning to think ..read more
Txtlab
10M ago
In this new essay out in New Literary History (open access here), we provide a framework for the empirical testing of narrative theory using the process of machine learning and predictive modeling. Drawing on a collection of over thirteen-thousand passages from an array of different genres, our models suggest that a very small number of ..read more
Txtlab
11M ago
I have a new piece out in the journal Poetics with Olivier Toubia, a professor of Business at Columbia University. We use word embeddings to model the linearity of narratives in a collection of ca. 2,300 books. We find that fiction exhibits a much stronger preference for non-linearity than non-fiction, but that this preference does ..read more
Txtlab
1y ago
Excited to announce a new dataset for the study of multilingual fiction developed by my student Sil Hamilton. Prior work in the Digital Humanities has highlighted the importance of multilingual corpora for cultural study (Mahony, 2018; Spence & Brandao, 2021; Gil & Ortega, 2016). In treating this absence, we present researchers with a dependable list of volumes ..read more
Txtlab
1y ago
We have a new paper out on the quantitative study of fictional things appearing as part of the Computational Humanities Research workshop. If you aren’t familiar with CHR I strongly recommend you check it out. It is a great venue for computational humanities research. Over ..read more
Txtlab
1y ago
I am delighted to announce a new lab initiative that is building a citizen science platform to annotate stories. We’re calling it Citizen Readers and the aim of the platform is to invite readers from around the world to help us better understand storytelling. While ..read more