Twitter Summarization Based on Social Network and Sparse Reconstruction

Authors: Ruifang He, Xingyi Duan

AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on this datasets show the effectiveness of our framework for handling the large scale short and noisy messages in social media.
Researcher Affiliation Academia Ruifang He, Xingyi Duan School of Computer Science and Technology, Tianjin University, Tianjin 300350, China Tianjin Key Laboratory of Cognitive Computing and Application, Tianjin 300350, China
Pseudocode Yes Algorithm 1 An Efficient Optimization Algorithm for SNSR
Open Source Code No The paper does not provide a statement or link indicating that the source code for their methodology is publicly available.
Open Datasets Yes We use the public Twitter data collected by University of Illinois1 as the raw data. 1https://wiki.illinois.edu/wiki/display/forward/Dataset-UDI -Twitter Crawl-Aug2012
Dataset Splits No The paper describes the creation of a "ground truth" corpus for evaluation, but does not specify explicit training, validation, and test splits for model development or hyperparameter tuning.
Hardware Specification No The paper does not provide specific details about the hardware used to run the experiments.
Software Dependencies No The paper does not list specific software components with version numbers required to replicate the experiments.
Experiment Setup Yes We tune four parameters greedily through setting step size, such as α in range [0, 1], setting step size as 0.01. Through preliminary experiments, we set α = 0.03, λ = 1, and γ = 1. And we set the similarity threshold θ = 0.1, which is consistent with the observation that the similarity between sentences is mostly distributed in the area of [0, 0.1].