Unsupervised Sentiment Analysis with Signed Social Networks

Authors: Kewei Cheng, Jundong Li, Jiliang Tang, Huan Liu

AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical experiments on two real-world datasets corroborate its effectiveness.
Researcher Affiliation Academia 1. Computer Science and Engineering, Arizona State University, Tempe, 85281, USA 2. Computer Science and Engineering, Michigan State University, East Lansing, 48824, USA
Pseudocode Yes Algorithm 1: Signed Senti Algorithm
Open Source Code No The paper does not provide any statement about making the source code available or include links to code repositories.
Open Datasets Yes We used two real-world datasets from Epinions and Slashdot which include both positive and negative links to perform unsupervised sentiment analysis. ... (Leskovec, Huttenlocher, and Kleinberg 2010b)
Dataset Splits No The paper does not explicitly provide training/validation/test dataset splits (e.g., percentages, sample counts, or specific methods for splitting).
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used to run the experiments.
Software Dependencies No The paper mentions using "Senti Word Net" as a sentiment lexicon but does not provide specific version numbers for any software dependencies or libraries used in the implementation or experimentation.
Experiment Setup Yes Noticed that in Sigend Senti, we have three regularization parameters α, β, γ. We empirically set these parameters as {α = 1, β = 0.5, γ = 0.7} in Epinions and {α = 1, β = 1, γ = 0.1} in Slashdot.