2015 International Conference on Advanced Computer Science and Information Systems (ICACSIS) 2015
DOI: 10.1109/icacsis.2015.7415168
|View full text |Cite
|
Sign up to set email alerts
|

Combination of singular value decomposition and K-means clustering methods for topic detection on Twitter

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
20
0

Year Published

2018
2018
2024
2024

Publication Types

Select...
5
4

Relationship

0
9

Authors

Journals

citations
Cited by 44 publications
(20 citation statements)
references
References 7 publications
0
20
0
Order By: Relevance
“…• Probabilistic Model -Latent Dirichlet Allocation (LDA) [18] • Clustering -Document-pivot (Doc-p) [19], BN-gram [11] • Frequent Pattern Mining -Soft Frequent Pattern Mining (SFPM) [11] • Matrix Factorization -SVD-KMean [20], SNMF-Orig, SNMF-KL [17] • Exemplar-Based -Exemplar [14] • Graph-based -Graph-based Feature-pivot (GFeat-p) [21] For the FA Cup dataset, Figure 7 shows the results for T-Recall at K = {2, 4, 6, . .…”
Section: Resultsmentioning
confidence: 99%
“…• Probabilistic Model -Latent Dirichlet Allocation (LDA) [18] • Clustering -Document-pivot (Doc-p) [19], BN-gram [11] • Frequent Pattern Mining -Soft Frequent Pattern Mining (SFPM) [11] • Matrix Factorization -SVD-KMean [20], SNMF-Orig, SNMF-KL [17] • Exemplar-Based -Exemplar [14] • Graph-based -Graph-based Feature-pivot (GFeat-p) [21] For the FA Cup dataset, Figure 7 shows the results for T-Recall at K = {2, 4, 6, . .…”
Section: Resultsmentioning
confidence: 99%
“…Clustering By considering the dynamicity and unpredictability of social media data streams, there has been a tendency to use clustering for event detection. McCreadie et al (2013) andNur'Aini et al (2015) showed that K-means clustering can be successfully used to extract events. In order to improve efficiency and effectiveness, they clustered low dimensional document vectors, which were generated using Locality Sensitive Hashing (LSH) and Singular Value Decomposition (SVD), respectively.…”
Section: Related Workmentioning
confidence: 99%
“…As token representations, self-learned word embeddings are used while preserving syntactical and semantical features of the underlying corpus. According to previous research, document clustering approaches were more popularly used with event detection (Nur'Aini et al 2015;Nguyen et al 2019;Comito et al 2019a, b). However, with the recent increments made to character limits by social media services (e.g.…”
Section: Cluster Change Calculationmentioning
confidence: 99%
“…For k-means, the singular value decomposition (SVD) is often used for dimensionality reduction [29]- [31]. The tandem of SVD and k-means clustering was applied to network applications [29], [32], in medical imaging [33] or FC analysis [20] and thoroughly studied in gene expression [30]. The denoising properties of the SVD are well understood, limiting the noise to the reduced signal subspace only [34].…”
Section: Related Work On Dimentionality Reductionmentioning
confidence: 99%