Hello #sleeppeepsaclanthology.org/2024.clpsych...
Lorenzo Bertolini, Valentina Elce, Adriana Michalak, Hanna-Sophia Widhoezl, Giulio Bernardi, Julie Weeds. Proceedings of the 9th Workshop on Computational Linguistics and Clinical Psychology (CLPsych ...
DReAMy abstract's finally out on SleepMedicine (WorldSleep 23)! www.sciencedirect.com/science/arti...
Overall, the work shows how LLMs can be adapted to annotate dream reports from different populations with minimal supervision, potentially allowing for standardised and replicable annotation of large datasets for research purposes!
Lastly, we tested if our model was robust to OoD unlabeled data from a subject with a diagnosed PTSD (a Veteran of the Vietnam War), and found that the model’s prediction fit the *expected* emotion distribution, without simply mimicking the training distribution.
We also conducted an ablation experiment, to understand if the performance was influenced by memorisation or implicit statistics within different series (subsets of DreamBank), but found no significant evidence of these differences impacting the model.
Our main results show a generally strong and stable performance across most single emotions and emotion sets, aside from a widespread poor performance for sadness.
