Investigating Rumor News Using Agreement-Aware Search

Shang, Jingbo; Shen, Jiaming; Sun, Tianhang; Liu, Xingbang; Gruenheid, Anja; Korn, Flip; Lelkes, Adam D.; Yu, Cong

doi:10.1145/3269206.3272020

Cited by 14 publications

(7 citation statements)

References 25 publications

(29 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, we only use the lead-3 sentences, since news articles tend to summarize the event at the very beginning. Such a strategy has been used in previous related work [25,32] and also serves as a strong baseline for the text summarization task [31].…”

Section: Iterative Key Event Document Selectionmentioning

confidence: 99%

Unsupervised Key Event Detection from Massive Text Corpora

Zhang,

Guo,

Shen

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Automated event detection from news corpora is a crucial task towards mining fast-evolving structured knowledge. As real-world events have different granularities, from the top-level themes to key events and then to event mentions corresponding to concrete actions, there are generally two lines of research: (1) theme detection tries to identify from a news corpus major themes (e.g., "2019 Hong Kong Protests" versus "2020 U.S. Presidential Election") which have very distinct semantics; and (2) action extraction aims to extract from a single document mention-level actions (e.g., "the police hit the left arm of the protester") that are often too fine-grained for comprehending the real-world event. In this paper, we propose a new task, key event detection at the intermediate level, which aims to detect from a news corpus key events (e.g., HK Airport Protest on Aug. 12-14), each happening at a particular time/location and focusing on the same topic. This task can bridge event understanding and structuring and is inherently challenging because of (1) the thematic and temporal closeness of different key events and (2) the scarcity of labeled data due to the fast-evolving nature of news articles. To address these challenges, we develop an unsupervised key event detection framework, EvMine, that (1) extracts temporally frequent peak phrases using a novel ttf-itf score, (2) merges peak phrases into event-indicative feature sets by detecting communities from our designed peak phrase graph that captures document cooccurrences, semantic similarities, and temporal closeness signals, and (3) iteratively retrieves documents related to each key event by training a classifier with automatically generated pseudo labels from the event-indicative feature sets and refining the detected key events using the retrieved documents in each iteration. Extensive experiments and case studies show EvMine outperforms all the baseline methods and its ablations on two real-world news corpora. CCS CONCEPTS• Information systems → Data mining; • Computing methodologies → Natural language processing.

show abstract

Section: Iterative Key Event Document Selectionmentioning

confidence: 99%

Unsupervised Key Event Detection from Massive Text Corpora

Zhang,

Guo,

Shen

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…They developed an agreement-aware search framework designed to provide users with a holistic view of a question, for which the ground truth was not confident. They designed a two-step model consisting of a tree-based model based on handcrafted features and an RNN plus attention model focusing on only a few key sentences [52]. The proposed model in [51] is a single, end-to-end ranking-based algorithm with MLP.…”

Section: Related Workmentioning

confidence: 99%

Fake News Stance Detection Using Deep Learning Architecture (CNN-LSTM)

et al. 2020

View full text Add to dashboard Cite

Society and individuals are negatively influenced both politically and socially by the widespread increase of fake news either way generated by humans or machines. In the era of social networks, the quick rotation of news makes it challenging to evaluate its reliability promptly. Therefore, automated fake news detection tools have become a crucial requirement. To address the aforementioned issue, a hybrid Neural Network architecture, that combines the capabilities of CNN and LSTM, is used with two different dimensionality reduction approaches, Principle Component Analysis (PCA) and Chi-Square. This work proposed to employ the dimensionality reduction techniques to reduce the dimensionality of the feature vectors before passing them to the classifier. To develop the reasoning, this work acquired a dataset from the Fake News Challenges (FNC) website which has four types of stances: agree, disagree, discuss, and unrelated. The nonlinear features are fed to PCA and chi-square which provides more contextual features for fake news detection. The motivation of this research is to determine the relative stance of a news article towards its headline. The proposed model improves results by ∼ 4% and ∼ 20% in terms of Accuracy and F 1 − score. The experimental results show that PCA outperforms than Chi-square and state-of-the-art methods with 97.8% accuracy.

show abstract

“…They created a contract-alert quest framework to offer consumers a complete picture of a topic for which the pulverized fact was uncertain. They created a dual-phase method that included a tree-built method with handmade features and an RNN with attention method that focused on solitary a rare important word [60]. TF-IDF was employed to excerpt features to epitomize both headings and body of news items in [61], which is a single, endways ranking-built procedure using MLP.…”

Section: Related Workmentioning

confidence: 99%

Early Detection of Fake News from Social Media Networks Using Computational Intelligence Approaches

Ogundokun

Arowolo

Misra

et al. 2021

Studies in Computational Intelligence

View full text Add to dashboard Cite

In recent years, misinformation which includes false news (FN) has become a worldwide issue owing to its exponential development, mostly on social media (SM). The broad dissemination of misinformation and FN can create harmful societal repercussions. Despite current improvements, spotting fake news remains difficult owing to its intricacy, multiplicity, multi-modality, and fact-scrutiny or annotation expenses. Therefore, there is a necessity for Computational Intelligence Approaches (CIA) that can identify this fake news automatically. This study projected using dimensionality reduction (DR) approach to decrease the dimensionality of the feature vectors before sending them to the classifiers. The study focuses on a computational intelligence-based fake news detection system and a novel approach of employing three CIA for the detection of FN was proposed. The CIA employed for this study are Genetic Algorithm (GA), K-Nearest Neighbor (KNN), and Bagged Ensembled Learning (BEL). The proposed system performance was evaluated utilizing confusion matrix measures like accuracy, sensitivity, specificity, precision, and f-measure. The system was compared with the existing system and it was deduced that the projected system outperformed that of existing systems with an accuracy of 99.28%, sensitivity of 99.28%, precision of 99.99%, and f-measure of 99.63%. In conclusion, it was discovered that GA + KNN performance in terms of accuracy, sensitivity, specificity, precision, and f-measure sur-passed that of the GA + BEL.

show abstract

Investigating Rumor News Using Agreement-Aware Search

Cited by 14 publications

References 25 publications

Unsupervised Key Event Detection from Massive Text Corpora

Unsupervised Key Event Detection from Massive Text Corpora

Fake News Stance Detection Using Deep Learning Architecture (CNN-LSTM)

Early Detection of Fake News from Social Media Networks Using Computational Intelligence Approaches

Contact Info

Product

Resources

About