Topic Extraction and Social Problem Detection Based on Document Clustering

Hashimoto, Taiichi; Murakami, Koji; Inui, Tomoyuki; Utsumi, Kazuo; Ishikawa, Masamichi

doi:10.3392/sociotechnica.5.216

Cited by 4 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used the scikit-learn API 7 for the implementation of LR and lightgbm 8 for the implementation of GBT. MLP and CNN were built using PyTorch 9 . As a hyperparameter for LR, the value of the l2 regularization coefficient was set to 10.…”

Section: Experiments 1: Claims-making Tweets Classificationmentioning

confidence: 99%

“…Most previous researches that attempted to extract social issues aimed to provide an overview of the social problems and applied text mining techniques to news channels and newspapers. Hashimoto et al extracted articles related to incidents or accidents from newspapers and applied hierarchical clustering to analyze the social issues by selecting important clusters [9]. Jeong et al extracted sentences that explained the social issues by using topic modeling to Korean newspapers and news channels [15].…”

Section: Related Workmentioning

confidence: 99%

“…In this study, we focus on the early extraction of viral spreading social issues to solve them expeditiously. However, previous methods proposed for the extraction of social issues are not suitable in this case because they only targeted news channels and newspapers [9,15,31]. News channels and newspapers are a good sources of information for extracting officially announced social issues because they are the epicenters of those issues.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Constructive Approach for Early Extraction of Viral Spreading Social Issues from Twitter

Jen

Ochi

Sakaki

et al. 2020

12th ACM Conference on Web Science

View full text Add to dashboard Cite

In recent years, there has been a rapid increase in viral spreading social issues that emerge in the public consciousness through the fast spread of information online. With the advent of social media, they sometimes yield unexpected side effects such as product boycotts. Therefore, it is important to recognize them as the earliest and take preventive measures against them. Existing researches on social issue extraction have mainly focused on news channels and newspapers as the primary information sources. However, such approaches cannot be applied for the early extraction of viral spreading social issues because their epicenter is the online public's opinion. In this study, we propose a constructive method inspired by a social issues research approach, called constructivism, for the early extraction of viral spreading social issues. It is characteristic that our method identifies the keywords related to social issues using information obtained from the claims-making activities on Twitter and Twitter-user clustering. We conducted experiments on a large Twitter dataset comprising tens of billions of tweets and the proposed method successfully extracted six out of the seven viral spreading social issues earlier than their first TV news coverage. Furthermore, the proposed method could identify such cases approximately two weeks earlier, on average, than the first national TV news coverage. CCS CONCEPTS • Information systems → Data extraction and integration.

show abstract

Section: Experiments 1: Claims-making Tweets Classificationmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Constructive Approach for Early Extraction of Viral Spreading Social Issues from Twitter

Jen

Ochi

Sakaki

et al. 2020

12th ACM Conference on Web Science

View full text Add to dashboard Cite

show abstract

Visualization of Potential Technical Solutions by Self-Organizing Maps and Co-Cluster Extraction

Nishida

Honda

2018

2018 Joint 10th International Conference on Soft Computing and Intelligent Systems (SCIS) and 19th International Symposium on A

View full text Add to dashboard Cite

Visualization of the Internet News Based on Efficient Self-Organizing Map Using Restricted Region Search and Dimensionality Reduction

Toyota¹,

Nobuhara²

2012

J. Adv. Comput. Intell. Intell. Inform.

View full text Add to dashboard Cite

In this paper, we propose a system to visualize the relationships in huge quantities of Internet news by twodimensional self-organizing maps instead of the conventional methods of listing Internet news. In the proposed method, morphological analysis is conducted on the texts of Internet news to generate input vectors with elements of keywords. The characteristics specific to Internet news that many of the vector elements become sparse allows dimensional reductions as well as speeding up of self-organizing mapping with restricted search regions in learning. We verify through evaluation experiments with the data of 80 pieces of news that the proposed system can reduce computation time by 75% to 99% and can create more efficient SOM compared with the generally available SOM.

show abstract

Topic Extraction and Social Problem Detection Based on Document Clustering

Cited by 4 publications

References 7 publications

Constructive Approach for Early Extraction of Viral Spreading Social Issues from Twitter

Constructive Approach for Early Extraction of Viral Spreading Social Issues from Twitter

Visualization of Potential Technical Solutions by Self-Organizing Maps and Co-Cluster Extraction

Visualization of the Internet News Based on Efficient Self-Organizing Map Using Restricted Region Search and Dimensionality Reduction

Contact Info

Product

Resources

About