Perceiving Topic Bubbles: Local Topic Detection in Spatio-Temporal Tweet Stream

Chen, Junsha; Gao, Neng; Xue, Cong; Zha, Daren

doi:10.1007/978-3-030-18579-4_43

Cited by 2 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Splitter [52] excavates fine grained sequential patterns in semantic trajectories. STREAMCUBE [53] can explore spatiotemporal activity with different spatial granularity, Both Chen et al [54] and ReAct [1] consider the continuity of time and space in the prediction of spatiotemporal activity. Although they fully develop the value of time and space, they do not make full use of text information.…”

Section: Related Workmentioning

confidence: 99%

A Fast Lightweight Spatiotemporal Activity Prediction Method

et al. 2019

View full text Add to dashboard Cite

How to predict spatiotemporal activity from geo-tagged social media is an urgent problem. Existing methods don't make full use of spatiotemporal information and text sequence features. In view of above problem, we design a Fast Lightweight Spatiotemporal Activity Prediction method(FLSAP) based on Gated Recurrent Unit(GRU) neural network. While GRU structure can extract text sequence features, the model takes up a lot of space due to the numerous parameters. At the same time, due to the long sequence in the text, the convergence speed of GRU is slow. So, we design a novel GRU neuron, GRU with Tiny and Skip(GTS), which can quickly generate a lightweight model with higher accuracy. In GTS, we add a scalar weighted residual connection to stabilize the training. Furthermore, we extend the residual connection to a gate by reusing the parameter matrices to compress the model size. At last, in order to make the model converge faster, we add a binary gate, which determine whether to skip the current state update. According to the experimental results, compared with ReAct [1] in the spatiotemporal activity prediction task, FLSAP improves the accuracy by 3.3%, reduces the model space by 98.79% and accelerates 74.4% of convergence speed.

show abstract

Section: Related Workmentioning

confidence: 99%