Towards Effective Event Detection, Tracking and Summarization on Microblog Data

Long, Rui; Wang, Haofen; Chen, Yuqiang; Jin, Ou; Yu, Yong

doi:10.1007/978-3-642-23535-1_55

Cited by 100 publications

(74 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The method is evaluated against a manually labeled result set for a one-month data set with 2.6 million tweets. Long et al [14] use divisive clustering, whereas Weng and Lee [21] use discrete wavelet analysis and graph partitioning. Both of these approaches use word frequencies of individual words for event detection.…”

Section: Introductionmentioning

confidence: 99%

Run-Time and Task-Based Performance of Event Detection Techniques for Twitter

Weiler

Grossniklaus

Scholl

2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Twitter's increasing popularity as a source of up to date news and information about current events has spawned a body of research on event detection techniques for social media data streams. Although all proposed approaches provide some evidence as to the quality of the detected events, none relate this task-based performance to their runtime performance in terms of processing speed or data throughput. In particular, neither a quantitative nor a comparative evaluation of these aspects has been performed to date. In this paper, we study the runtime and task-based performance of several state-of-the-art event detection techniques for Twitter. In order to reproducibly compare run-time performance, our approach is based on a general-purpose data stream management system, whereas task-based performance is automatically assessed based on a series of novel measures.

show abstract

Section: Introductionmentioning

confidence: 99%

Run-Time and Task-Based Performance of Event Detection Techniques for Twitter

Weiler

Grossniklaus

Scholl

2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…But sometimes only one sentence is not enough for introducing an event. Rui Long et al [3] proposed a unified workflow of event detection, tracking and summarization on microblog data. Their summarization step considered both the content coverage and evolution over time.…”

Section: Related Workmentioning

confidence: 99%

“…However, words only are uneasy for people to understand an event. Other works select some posts to represent an event [3]. Due to the characteristic of microblog, this method can involve much irrelevant information.…”

Section: Related Workmentioning

confidence: 99%

“…In the traditional multi-document summarization task, ROUGE is a widely used standard which measures the similarity between a generated summary and some manual labeled summaries of experts [23]. In this paper, since we do not have manually labeled summary in hand, we reference the method mentioned in [3] which uses precision@n (Pre@n) to assess the relevance of an event summary. Note that n denotes the number of posts selected to represent an event.…”

Section: Event Summary Generationmentioning

confidence: 99%

See 1 more Smart Citation

Event Detection and Summarization on Microblogs

Zhao¹,

Liu²,

Cui³

2016

IJGDC

View full text Add to dashboard Cite

show abstract

“…Most prior works are on event-level or topic-level summarization. Typically, the first step is to cluster posts into sub-events (Chakrabarti and Punera, 2011;Duan et al, 2012;Shen et al, 2013) or subtopics (Long et al, 2011;Rosa et al, 2011;Meng et al, 2012), and then the second step generates summary for each cluster.…”

Section: Related Workmentioning

confidence: 99%

Using Content-level Structures for Summarizing Microblog Repost Trees

Gao²,

Wei³

et al. 2015

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

A microblog repost tree provides strong clues on how an event described therein develops. To help social media users capture the main clues of events on microblogging sites, we propose a novel repost tree summarization framework by effectively differentiating two kinds of messages on repost trees called leaders and followers, which are derived from contentlevel structure information, i.e., contents of messages and the reposting relations. To this end, Conditional Random Fields (CRF) model is used to detect leaders across repost tree paths. We then present a variant of random-walk-based summarization model to rank and select salient messages based on the result of leader detection. To reduce the error propagation cascaded from leader detection, we improve the framework by enhancing the random walk with adjustment steps for sampling from leader probabilities given all the reposting messages. For evaluation, we construct two annotated corpora, one for leader detection, and the other for repost tree summarization. Experimental results confirm the effectiveness of our method.

show abstract

Towards Effective Event Detection, Tracking and Summarization on Microblog Data

Cited by 100 publications

References 3 publications

Run-Time and Task-Based Performance of Event Detection Techniques for Twitter

Run-Time and Task-Based Performance of Event Detection Techniques for Twitter

Event Detection and Summarization on Microblogs

Using Content-level Structures for Summarizing Microblog Repost Trees

Contact Info

Product

Resources

About