News Verification by Exploiting Conflicting Social Viewpoints in Microblogs

Authors: Zhiwei Jin, Juan Cao, Yongdong Zhang, Jiebo Luo

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments conducted on a real-world data set show that the news verification performance of our approach significantly outperforms those of the baseline approaches. Experiments Data Set News verification on social media is a fairly new problem, no standard data set is publicly available at the moment.
Researcher Affiliation Academia 1Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, CAS, Beijing 100190, China 2University of Chinese Academy of Sciences, Beijing 100049, China 3University of Rochester, Rochester, NY 14627, USA
Pseudocode No The paper describes algorithmic steps but does not include a formally structured pseudocode block or an 'Algorithm' figure.
Open Source Code No The paper does not provide any concrete statement or link regarding the public availability of its source code.
Open Datasets No Therefore, we build a data set collected from Sina Weibo for performance evaluation. This data set contains 73 fake news and 73 real news composed of 49,713 tweets, and involves 42,310 distinct users (Table 1). The paper does not provide access information for this dataset.
Dataset Splits Yes Reported result comes from a decision tree classifier through standard 4-fold cross validation procedure. ... The reported results are gained with a 4-fold cross validation.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used for running the experiments.
Software Dependencies No The paper mentions software components like 'decision tree classifier', 'SVM classifier', 'LDA topic model', and 'constrained k-means clustering algorithm' but does not provide specific version numbers for any of them.
Experiment Setup Yes For conflicting viewpoints mining, we take the same hyper-parameter settings in (Trabelsi and Zaiane 2014) for topic model, and we set the topics number K = 10, viewpoints number fixed as 2 and viewpoints clustering threshold h = 0.95. For regularization parameter in (5), we take the setting in (Zhou et al. 2004) as 0.99.