Ensemble Algorithms for Microblog Summarization

Dutta, Soumi; Chandra, Vibhash; Mehra, Kanav; Das, Asit Kumar; Chakraborty, Tanmoy; Ghosh, Saptarshi

doi:10.1109/mis.2018.033001411

Cited by 46 publications

(20 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The isomorphic base classifier (or regressor) uses intelligent algorithms, while the isomeric base classifier uses different types of intelligent algorithms or uses the same type of intelligent algorithms but with different parameters. Bagging and boosting are two frameworks that are typically applied to isomorphic ensemble learning, while stacked generalisation is commonly used in isomeric ensemble learning [19]. The output of a base-learner regression model at Level 0 is used as the input of a regression model at Level 1, and the regression model at Level 1 is referred to as a meta-learner or generaliser.…”

Section: Predictive Model Of Eddy Current Losses Of a Large Turbogenementioning

confidence: 99%

Finite‐element analysis combined with an ensemble Gaussian process regression to predict the damper eddy current losses in a large turbo‐generator

Zhao

Guo

Wang

et al. 2020

IET Science, Measurement & Technology

View full text Add to dashboard Cite

Section: Predictive Model Of Eddy Current Losses Of a Large Turbogenementioning

confidence: 99%

Finite‐element analysis combined with an ensemble Gaussian process regression to predict the damper eddy current losses in a large turbo‐generator

Zhao

Guo

Wang

et al. 2020

IET Science, Measurement & Technology

View full text Add to dashboard Cite

“…This includes socio-political events, natural and manmade disasters, etc. On such sites, micro-blogs are usually posted so quickly and in such enormous volumes, that humans can't run through all the posts [12]. The huge chunk of data emanating from all such sources contribute to what is known as Big Data.…”

Section: The Importance Of Data Summarizationmentioning

confidence: 99%

“…Especially, crowd-sourced textual data from social media sites like Twitter and Flickr are nowadays important sources of real-time information on ongoing events, including socio-political events, natural and manmade disasters, and so on. On such sites, micro-blogs are usually posted so rapidly and in such large volumes, that it is not feasible for human users to go through all the posts [12].…”

Section: The Importance Of Data Summarizationmentioning

confidence: 99%

Data Summarization and Modelling

Kalathil¹

2020

RCES

View full text Add to dashboard Cite

Data analytics find a myriad of applications in all walks of human endeavour. The modern world is characterized by huge amounts of data emerging from all human-made systems, including sensors, communication devices, signal processors and conditioners. The plethora of data originating from several sources often have to be cleaned and filtered to make it useful for further processing. In this paper, we discuss a very important domain in Big Data processing-namely, Data Summarization and its modelling. Big Data refers to the fairly huge chunks of data originating from several real-world sources, including those from all communication systems (including voice, text-data, images, and video), sensing devices (for example, those from sensors in a wired or wireless sensor network), digital data processors and several other natural sources including those from galactic sources from other planets and stars outside our galaxy. To effectively process the data, even with the almost seamless processing power of modern-day digital computers, one has to resort to Data Summarization. Modelling is another key component in visualizing the impact of such pre-processed data to arrive at meaningful conclusions on the processes which are being studied.

show abstract

“…However, in order to process incoming tweets to perform quick response operation, two challenges may arise: (a) availability of vast amount of tweets having varied characteristics including sympathy and emotions, personal opinion, among others. In the literature [2]- [4], the importance of situational tweets has already been shown and the importance of separating situational tweets from non-situational is also established; (b) rapid rate of posting such tweets: this may cause the overload problem.…”

Section: Introductionmentioning

confidence: 99%

DCBRTS: A Classification-Summarization Approach for Evolving Tweet Streams in Multiobjective Optimization Framework

Bansal

Saini²,

Saha

2021

IEEE Access

View full text Add to dashboard Cite

The emergence of social media platforms like Twitter has become a prominent communication source in disaster outbreak. NGOs, Government agencies leverage twitter's open and public features to provide immediate relief. Nevertheless, situational information gets immersed in millions of tweets with varying characteristics. Examining each tweet can be cumbersome and time-consuming. Thus, the efficient extraction of disaster-related tweets and getting information from all the extracted tweets is required. In the current paper, we have developed a novel framework that uses a deep learning-based classification model to separate the situational tweets from others and summarize them in real-time. Our system is a three-phase process: (a) Creating tweet clusters using a representative set of tweets from the initial set of extracted tweets using a multi-objective optimization concept; (b) When a new tweet arrives, the clusters are updated. The new tweet is classified as situational vs. non-situational. If situational, it is assigned to the closest cluster or new cluster. This assignment is based on its weighted average of syntactic and semantic distances and relevancy to the cluster; (c) Summary is formulated by extracting tweets from each cluster. The proposed approach's superior performance on four datasets related to different disaster-related events indicates the developed framework's efficiency over state-of-the-art techniques.

show abstract

Ensemble Algorithms for Microblog Summarization

Cited by 46 publications

References 12 publications

Finite‐element analysis combined with an ensemble Gaussian process regression to predict the damper eddy current losses in a large turbo‐generator

Finite‐element analysis combined with an ensemble Gaussian process regression to predict the damper eddy current losses in a large turbo‐generator

Data Summarization and Modelling

DCBRTS: A Classification-Summarization Approach for Evolving Tweet Streams in Multiobjective Optimization Framework

Contact Info

Product

Resources

About