Acquiring Knowledge of Affective Events from Blogs Using Label Propagation

Authors: Haibo Ding, Ellen Riloff

AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our research creates an event context graph from a large collection of blog posts and uses a sentiment classifier and semi-supervised label propagation algorithm to discover affective events. We explore several graph configurations that propagate affective polarity across edges using local context, discourse proximity, and event-event co-occurrence. We then harvest highly affective events from the graph and evaluate the agreement of the polarities with human judgements.
Researcher Affiliation Academia Haibo Ding and Ellen Riloff School of Computing University of Utah Salt Lake City, UT 84112 {hbding, riloff}@cs.utah.edu
Pseudocode Yes The pseudocode for our implementation is shown in Algorithm 1.
Open Source Code No The paper does not contain any statement or link indicating that the source code for the methodology is openly available.
Open Datasets Yes For our research, we used the personal story corpus compiled by Gordon & Swanson (2008), who created a system to identify stories that are primarily a first person description of events in the life of the author .
Dataset Splits Yes To evaluate its performance, we trained the classifier on 6425 of the annotated tweets and tested it on the remaining 1564 tweets.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., GPU models, CPU types, memory) used to run the experiments.
Software Dependencies No The paper mentions using "Stanford Core NLP tools (Manning et al. 2014)" but does not specify version numbers for this or any other software dependencies, which is necessary for reproducibility.
Experiment Setup Yes In our experiments we set τ = 0.5. For our experiments, we ran label propagation until the values converged or it ran for 100 iterations. We set the weight for an edge linking sentence si and sj to be w(si, sj) = 0.804