Automatic Tweet Detection based on Data Specified through News Production

Goto, Jun; Miyazaki, Tatsuya; Takei, Yasuhiko; Makino, Kiminobu

doi:10.1145/3180308.3180309

Cited by 5 publications

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To solve the problem of the high computational cost of event detection, Hasan et al [24] proposed the event detection system of Twitter News+, which combined the word vector based on a random index with the text of position-sensitive hash, and used incremental clustering method to cluster the event-related tweets together, which not only reduced the computational cost but also improved the efficiency of event detection. Goto et al [25] designed an automatic tweet detection system based on a character-based bi-directional long-and short-term memory and attention mechanism, which can obtain useful information from social media for news production. However, because the dataset contains a large number of colloquial words, Internet buzzwords, unknown links, and other information, a large amount of noisy data will be introduced when clustering, affecting detection accuracy.…”

Section: Related Workmentioning

confidence: 99%

A Novel Burst Event Detection Model Based on Cross Social Media Influence

Ban

Zhang

Dong-jun

et al. 2022

Preprint

View full text Add to dashboard Cite

With the frequent occurrence of public emergencies around the world today, how to effectively use big data and artificial intelligence technologies to accurately and efficiently detect and identify burst events of the Internet has become a hot issue. These existing burst event detection methods lack of comprehensively considering multi-data source of social media and their influences, which leads to a lower accuracy. This paper proposes a novel burst event detection model based on cross social media influence and unsupervised clustering. In this article, we, explain the basic framework of burst event detection, along with characteristics of social media influence, and the word frequency features and growth rate features. In our proposed approach, according to the time information in the data stream, social media network data were sliced and the burst word features in each time window were calculated. Then, the three burst features were fused to compute the burst degree of words; after that the words larger than the threshold were selected to form the burst word set. Finally, the agglomerative hierarchical clustering method is introduced to cluster the burst word set and extracts the burst event from it. The results of the experiment on a real-world social media dataset show that the detection method has significantly improved in Precision and F1-score value compared with the latest four burst event detection methods and prove the effectiveness of the proposed method.

show abstract

Section: Related Workmentioning

confidence: 99%