CDS: Collaborative distant supervision for Twitter account classification

Cui, Lishan; Zhang, Xiuzhen; Qin, A. K.; Sellis, Timos; Wu, Lifang

doi:10.1016/j.eswa.2017.03.075

Cited by 10 publications

(7 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The tweets were from a variety of domains, topics and time period (referred as topic specific/topic oriented tweets). These prominently included tweets from or about elite personalities like actors; singers; sportsperson; comedians; politicians, authors, idols; entertainers, 28,34,37,40,54,55,67,70,73,75,79 etc, news and commemoratives, 17,30,48,58,59,64,67,79 health and fitness, 31,56,57,69,74,75,78,79 stock market exchanges, 29,34,63,82 companies like AT&T; Amazon;…”

Section: • Widely Used Datasets and Domains In Which The Studies For mentioning

confidence: 99%

“…Recall (R)/ Sensitivity (Sn) It defines the sensitivity or the completeness of any classifier. 27-29,31-33,35,37-39,43-45,47,49-51,57-59, A higher recall value indicates less ''false positives'' and vice 61,62,64,66,68,70,74,75,81,83,84 versa. Recall and precision are bounded by inverse relation with each other.…”

mentioning

confidence: 99%

“…Accuracy (A) It is defined as proximity of a measurement to its true value. It 17,29,40,43-45,48-50,52,55,57,60,64, is calculated as a proportion of TP and true negatives (TN) 66,[68][69][70][72][73][74][75][77][78][79]85,[81][82][83] among total inspected cases.…”

mentioning

confidence: 99%

“…F score/F1 score/ It is defined as ''weighted'' harmonic mean of Recall and 27-35,37-39,43,44,47,49-51,53,54,59,61,62, F measure/F1 measure/F1 value(F) Precision. It is the combination of the precision and recall [66][67][68]70,74,75,81,83,84 measures.…”

mentioning

confidence: 99%

“…A higher precision27-29,31-33,35,37-39,43-45,47,49-51,56-62, value indicates fewer ''false positives'' (FP) and vice versa. It is64,66,68,70,74,75,80,81,83,84…”

mentioning

confidence: 99%

See 4 more Smart Citations

Systematic literature review of sentiment analysis on Twitter using soft computing techniques

Kumar

Jaiswal

2019

Concurrency and Computation

131

View full text Add to dashboard Cite

Sentiment detection and classification is the latest fad for social analytics on Web. With the array of practical applications in healthcare, finance, media, consumer markets, and government, distilling the voice of public to gain insight to target information and reviews is non-trivial. With a marked increase in the size, subjectivity, and diversity of social web-data, the vagueness, uncertainty and imprecision within the information has increased manifold. Soft computing techniques have been used to handle this fuzziness in practical applications. This work is a study to understand the feasibility, scope and relevance of this alliance of using Soft computing techniques for sentiment analysis on Twitter. We present a systematic literature review to collate, explore, understand and analyze the efforts and trends in a well-structured manner to identify research gaps defining the future prospects of this coupling. The contribution of this paper is significant because firstly the primary focus is to study and evaluate the use of soft computing techniques for sentiment analysis on Twitter and secondly as compared to the previous reviews we adopt a systematic approach to identify, gather empirical evidence, interpret results, critically analyze, and integrate the findings of all relevant high-quality studies to address specific research questions pertaining to the defined research domain. KEYWORDS machine learning, review, sentiment analysis, soft computing, Twitter INTRODUCTIONThe incessantly evolving dynamics of the Web in terms of the volume, velocity and variety of opinion-rich information accessible online, has made research in the domain of Sentiment Analysis (SA) a trend for many practical applications which facilitate decision support and deliver targeted information to domain analysts. Interestingly, the buzzing term ''big data'' which is estimated to be 90% unstructured 1 further makes it crucial to tap and analyze information using contemporary tools. Text mining models define the process to transform and substitute this unstructured data into a structured one for knowledge discovery. Use of classification algorithms to intelligently mine text has been studied extensively across literature. 2,3 SA, established as a typical text classification task, 4 is defined as the computational study of people's opinions, attitudes and emotions towards an entity. 5,6 It offers a technology-based solution to understand people's reactions, views and opinion polarities (positive, negative or neutral) in textual content available over social media sources.Research studies and practical applications in the field of SA have escalated in the past decade with the transformation and expansion of Web from passive provider of content to an active socially-aware distributor of collective intelligence. This new collaborative Web (called Web 2.0), 7 extended by Web-based technologies like comments, blogs and wikis, social media portals like Twitter or Facebook, that allow to build social networks based on professional relationship, i...

show abstract

Section: • Widely Used Datasets and Domains In Which The Studies For mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

“…A higher precision27-29,31-33,35,37-39,43-45,47,49-51,56-62, value indicates fewer ''false positives'' (FP) and vice versa. It is64,66,68,70,74,75,80,81,83,84…”

mentioning

confidence: 99%

See 3 more Smart Citations