Graph Clustering-Based Emerging Event Detection from Twitter Data Stream

Manaskasemsak, Bundit; Chinthanet, Bodin; Rungsawang, Arnon

doi:10.1145/3033288.3033312

Cited by 14 publications

(17 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the precision percentage that has obtained was not high and the model has not given a clear summary for the discovered events. Manaskasemsak et al (2016) divided Twitter stream into two-time windows of 15 days. Subsequently, Markov Clustering Algorithm (MCA) was employed to detect events from the undirected weighted graph which has built from features extracted using TFIDF.…”

Section: Graph-based Clustering Methodsmentioning

confidence: 99%

“…Different from Twitter, some SNs (e.g., Facebook) have privacy issues that limit the collection process to just offline publicly available data that have been given permissions to be collected (Chen et al, 2016). Becker et al (2011a;Phuvipadawat and Murata, 2010;Sakaki et al, 2010;Popescu et al, 2011;Ritter et al, 2012;Li et al, 2012a;Weng and Lee, 2011;Sankaranarayanan et al, 2009;Culotta, 2010;Osborne et al, 2012;Subašić and Berendt, 2011;Becker et al, 2012;Abhik and Toshniwal, 2013;Petrović et al, 2010;Ishikawa et al, 2012;Mathioudakis and Koudas, 2010;Long et al, 2011;Rosa et al, 2011;Popescu and Pennacchiotti, 2010;Benson et al, 2011;Lee and Sumiya, 2010;Mehrotra et al, 2013;Rajani et al, 2014;Weng et al, 2010;Zhao et al, 2011;Diao et al, 2012;Dong et al, 2015;Fang et al, 2014;Cataldi et al, 2010;Cordeiro, 2012;Kwan et al, 2013;Weiler et al, 2014;Aggarwal and Subbian, 2012;Tembhurnikar and Patil, 2015;Katragadda et al, 2017;Manaskasemsak et al, 2016;Zhang et al, 2015;Huang et al, 2013;Kaleel et al, 2013;Rafea an...…”

Section: Concepts Of Event Detectionmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Event Detection Models for Text Data Streams

Al-Dyani¹,

Ahmad²,

Kamaruddin³

2020

Journal of Computer Science

View full text Add to dashboard Cite

Event Detection (ED) is a study area that attracts the attention of decision-makers from various disciplines in order to help them in taking the right decision. ED has been examined on various text streams like Twitter, Facebook, Emails, Blogs, Web Forums and newswires. Many ED models have been proposed in literature. In general, ED model consists of six main phases: Data collection, pre-processing, feature selection, event detection, performance evaluation and result representation. Among these phases, event detection phase has a vital rule in the performance of the ED model. Consequently, numerous supervised, unsupervised, semi-supervised detection methods have been introduced for this phase. However, unsupervised methods have been extensively utilized as ED process is considered as unsupervised task. Hence, such methods need to be categorized on such a way so it can help researchers to understand and identified the limitations lay in these methods. In this survey, ED models for text data from various Social Network sites (SNs) are analyzed based on domain type, detection methods, type of detection task. In addition, main categories for unsupervised detection methods are explicitly mentioned with revising their related works. Moreover, the major open challenges faced by researchers for building ED models are explained and discussed in detail. The main objective of this survey paper is to provide a complete view of the recent developments in ED field. Hence, help scholars to identify the limitations of existing ED models for text data and help them to recognize the interesting future works directions.

show abstract

Section: Graph-based Clustering Methodsmentioning

confidence: 99%

Section: Concepts Of Event Detectionmentioning

confidence: 99%

A Survey on Event Detection Models for Text Data Streams

Al-Dyani¹,

Ahmad²,

Kamaruddin³

2020

Journal of Computer Science

View full text Add to dashboard Cite

show abstract

“…Furthermore, if no previous knowledge about the type of crisis and hence no keywords are available, the user can track all social media data for a selected region without entering any specific keywords. Because the system is able to track bursts resulting from increasing numbers of similar messages or evolving geotopic clusters, new unexpected events can be detected [23]. If the number of messages relating to any tracked query reaches some predefined thresholds, an automatic alert, in form of a visual or acoustical signal, is triggered.…”

Section: Design and Evaluationmentioning

confidence: 99%

The Usage of Twitter Data for Early Crisis Detection

Mirbabaie¹,

Stieglitz²,

Lambertz³

2020

WI2020 Community Tracks

View full text Add to dashboard Cite

The establishment of novel information and communications technologies, such as social media, has changed how individuals and organizations behave. Particularly during uncertain situations caused by natural or man-made disasters, people communicate and share information via social media. Emergency services could use published content of social media participants for an early detection of crisis situations and thus enhance crisis management. However, exploiting these information bears several challenges. To gain insights from large amounts of unstructured data in time-critical situations, emergency services are in the need of tools that enable them to gather, process, and analyze relevant information. In this research article, we follow the design science paradigm and propose a concept (artifact) of an early crisis detection tool. Based on expert interviews, design implications for the concept tool are derived. In addition, we conducted a design thinking workshop to evaluate the artifact, highlighting its practical relevance and usability.

show abstract

“…F ∈ Vt is an n-dimensional optimal features F = {F1, F2, …., Fn}, which have obtained from previous phase and represent a set of nodes within the time interval t. Subsequently, a weight w ∈ Wt will be assigned to the edge e (F1, F2) ∈ Et. The weight is calculated using the following adapted Equation which was proposed in [22]:…”

Section: Event Detection Phasementioning

confidence: 99%

“…Additionally, they generate good clustering results and has the ability to deal well with noisy contents [27]. On top of all that, they does not require to specify the number of clusters in advance and this is ideal as events often occur without prior warning or knowledge [22]. Therefore, a dynamic graph-based technique is used by this study to identify the clusters from the undirected weighted graph.…”

Section: Event Detection Phasementioning

confidence: 99%

Event Detection Model for Facebook News Posts

Al-Dyani,

Ahmad*,

Kamaruddin

2019

IJITEE

View full text Add to dashboard Cite

Event detection has wide application especially in the area of news streams analyzing where there is a need to monitor what events are emerging and affecting people’s lives. This is crucial for public administrations and policy makers to learn from their previous mistakes to make better decisions in the future. Different researchers have introduced several event detection models for Facebook news posts in. However, majority of these models have not provided adequate information about the discovered news events such as location, people and activity. In addition, existing models have ignored the problem of high dimensional feature space which affects the overall detection performance of the models. This research presents a conceptual event detection model for mining events from large volume of short text Facebook news posts and summarize their valuable information. This is crucial for public administrations and policy makers to learn from their previous mistakes to make better decisions in the future. The proposed model includes pre-processing, feature selection, event detection and summarization phases. The pre-processing phase involves several steps to convert unstructured text news posts into structure data. Feature selection phase to select the optimal feature subset. Meanwhile, event detection phase uses these features to construct undirected weighted graph and apply dynamic graph technique to identify the clusters from the graph and then annotate each cluster to its corresponding event. At the end of this paper, several unresolved problems in the construction of event detection model from Facebook news posts are reported to be used as future work for the current study.

show abstract

Graph Clustering-Based Emerging Event Detection from Twitter Data Stream

Cited by 14 publications

References 18 publications

A Survey on Event Detection Models for Text Data Streams

A Survey on Event Detection Models for Text Data Streams

The Usage of Twitter Data for Early Crisis Detection

Event Detection Model for Facebook News Posts

Contact Info

Product

Resources

About