An Overview of Sentiment Analysis in Social Media and Its Applications in Disaster Relief

Beigi, Ghazaleh; Hu, Xia; Maciejewski, Ross; Liu, Huan

doi:10.1007/978-3-319-30319-2_13

Cited by 166 publications

(104 citation statements)

References 80 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…According to him, processing of user-generated content through a robust SBI system could prove invaluable for political entities in order to align their governmental decisions with environmental trends and public opinion. Finally, Beigi et al (2016) explore crisis and disaster management through sentiment analysis and social media visual analytics. According to them, individual posts in social media about natural disasters and emergencies can be used as inputs in governmental SBI systems "to improve situational awareness and crisis management (…) while assisting in locating people who are in specific need during emergency situations".…”

Section: Educationmentioning

confidence: 99%

Social business intelligence: Review and research directions

Gioti¹,

Ponis²,

Panayiotou³

2018

JISIB

View full text Add to dashboard Cite

Social business intelligence (SBI) is a rather novel discipline, emerged in theacademic and business literature as a result of the convergence of two distinct researchdomains: business intelligence (BI) and social media. Traditional BI scientists and practitioners,after an inevitable initial shock, are currently discovering and acknowledge the potential of usergenerated content (UGD) published in social media as an invaluable and inexhaustible sourceof information capable of supporting a wide range of business activities. The confluence of thesetwo emerging domains is already producing new added value organizational processes andenhanced business capabilities utilized by companies all over the world to effectively harnesssocial media data and analyze them in order to produce added value information such ascustomer profiles and demographics, search habits, and social behaviors. Currently the SBIdomain is largely uncharted, characterized by controversial definitions of terms and concepts,fragmented and isolated research efforts, obstacles created by proprietary data, systems andtechnologies that are not mature yet. This paper aspires to be one of the few -to our knowledge contemporaryefforts to explore the SBI scientific field, clarify definitions and concepts,structure the documented research efforts in the area and finally formulate an agenda of futureresearch based on the identification of current research shortcomings and limitations.

show abstract

Section: Educationmentioning

confidence: 99%

Social business intelligence: Review and research directions

Gioti¹,

Ponis²,

Panayiotou³

2018

JISIB

View full text Add to dashboard Cite

show abstract

“…Recently, researchers have turned their attention to exploring sentiment analysis on the social media posts of individuals during natural disasters and emergencies (Beigi et al, 2016;Buscaldi and Hernandez-Farias, 2015;Caragea et al, 2014;Kryvasheyeu et al, 2015;Mandel et al, 2012;Shalunts et al, 2014). For example, a sentiment analysis system is applied for Italian to a set of tweets during the Genoa flooding (Buscaldi and Hernandez-Farias, 2015).…”

Section: Related Workmentioning

confidence: 99%

Identifying and Tracking Sentiments and Topics from Social Media Texts during Natural Disasters

Yang¹,

Mei²,

Ji³

et al. 2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

We study the problem of identifying the topics and sentiments and tracking their shifts from social media texts in different geographical regions during emergencies and disasters. We propose a location-based dynamic sentiment-topic model (LDST) which can jointly model topic, sentiment, time and Geolocation information. The experimental results demonstrate that LDST performs very well at discovering topics and sentiments from social media and tracking their shifts in different geographical regions during emergencies and disasters 1 .

show abstract

“…Public sentiment is an aggregation of individuals' sentiments, each of which is typically labeled as negative, neutral, or positive (Beigi et al 2016). Naturally, sentiment probabilities, which represent ratios for the three sentiments in the interest population, are basic predictors for estimating public sentiment (Yu and Kak 2012).…”

Section: Introductionmentioning

confidence: 99%

A Bayesian-Based Approach for Public Sentiment Modeling

Chen¹,

Ji²,

Wang³

2019

2019 Winter Simulation Conference (WSC)

View full text Add to dashboard Cite

Public sentiment is a direct public-centric indicator for the success of effective action planning. Despite its importance, systematic modeling of public sentiment remains untapped in previous studies. This research aims to develop a Bayesian-based approach for quantitative public sentiment modeling, which is capable of incorporating uncertainty and guiding the selection of public sentiment measures. This study comprises three steps: (1) quantifying prior sentiment information and new sentiment observations with Dirichlet distribution and multinomial distribution respectively; (2) deriving the posterior distribution of sentiment probabilities through incorporating the Dirichlet distribution and multinomial distribution via Bayesian inference; and (3) measuring public sentiment through aggregating sampled sets of sentiment probabilities with an application-based measure. A case study on Hurricane Harvey is provided to demonstrate the feasibility and applicability of the proposed approach. The developed approach also has the potential to be generalized to model various types of probability-based measures.

show abstract

An Overview of Sentiment Analysis in Social Media and Its Applications in Disaster Relief

Cited by 166 publications

References 80 publications

Social business intelligence: Review and research directions

Social business intelligence: Review and research directions

Identifying and Tracking Sentiments and Topics from Social Media Texts during Natural Disasters

A Bayesian-Based Approach for Public Sentiment Modeling

Contact Info

Product

Resources

About