Enhancing Social Media Analysis with Visual Data Analytics: A Deep Learning Approach

Shin, Donghyuk; He, Shu; Lee, Gene Moo; Whinston, Andrew B.; Cetintas, Suleyman; Lee, Kuang-Chih

doi:10.25300/misq/2020/14870

Cited by 115 publications

(57 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such DVA systems offer users a thorough understanding of a model and hints on how to troubleshoot and develop it. In the recent years, several studies have been conducted, where DVA has proven their effective and noteworthy impact in many fields, especially in big data analysis [115], human cognitive and perception science [154], analyze [43] IEEE VCG Yue, Xuanwu, (2019) [146] PhD diss Singh, (2019) [118] IJAIS 2018 Kwon et al, (2018) [66] IEEE VIS Cashman et al, (2018) [12] IEEE CGA Garcia et al, (2018) [34] CG Peixinho et al, (2018) [100] CGIP [19] IEEE CGA Yue et al, (2018) [147] IEEE VCG 2017 [76] IEEE ITS Pezzotti et al, (2017) [101] IEEE VCG Wongsuphasawat et al, (2017) [141] IEEE VCG Samek et al, (2017) [110] arXiv Leite et al, (2017) [70] IEEE VCG healthcare systems [72], and tourism management system [14]. In addition, DVA has the greatest impact of synthesizing information, deriving insights from massive, ambiguous, unstructured, unexpected patterns, decision making, and communicating assessment for action [59].…”

Section: Impact Of Deep Visual Analyticsmentioning

confidence: 99%

Deep Visual Analytics (DVA): Applications, Challenges and Future Directions

Islam¹,

Akter²,

Ratan³

et al. 2021

HCIS

View full text Add to dashboard Cite

Visual interactive system (VIS) has been received significant attention for solving various complex problems. However, designing and implementing a novel VIS with the large scale of data is a challenging task. While existing studies have applied various visual analytics (VA) to analyze and visualize insightful information, deep visual analytics (DVA) have considered as a promising technique to provide input evidences and explain system results. In this study, we present several deep learning (DL) techniques for analyzing data with visualization, which summarizes the state-of-the-art review on (i) big data analysis, (ii) cognitive and perception science, (iii) customer behavior analysis, (iv) natural language processing, (v) recommended system, (vi) healthcare analysis, (vii) fintech ecosystem, and (viii) tourism management. We present open research challenges for emerging DVA in the visualization community. We also highlight some key themes from the existing literature that may help to explore for future study. Thus, our goal is to help readers and researchers in DL and VA to understand key aspects in designing VIS for analysing data.

show abstract

Section: Impact Of Deep Visual Analyticsmentioning

confidence: 99%

Deep Visual Analytics (DVA): Applications, Challenges and Future Directions

Islam¹,

Akter²,

Ratan³

et al. 2021

HCIS

View full text Add to dashboard Cite

show abstract

“…Two out-of-the-box dashboard templates are available for image analysis: Brandwatch Logo Wall which displays images and corresponding captions based on the specific logo(s) that were selected in the query, and Brandwatch Image Analysis , which visually summarizes the content within the selected image data. The platform uses image recognition technology (Shin et al 2020 ), which can separately identify and classify the different objects, scenes, actions, and logos appearing in images. Figure 7 provides an example of this analysis on a sample of electric vehicle topics (Brandwatch 2021c ).…”

Section: Brandwatch For Classrooms Product Reviewmentioning

confidence: 99%

“…It is important to include readings and lectures on topics such as NLP (Hair Jr. et al 2021) and image analytics (Shin et al 2020 ) during this learning phase to provide a deeper understanding of the concepts and theories underlying these emerging technologies and their applications in a marketing environment.…”

Section: Integrating a Social Listening Platform Into A Marketing Analytics Course Designmentioning

confidence: 99%

“…Image analytics is an emerging SMA field of study, which includes the analysis and classification of images and visual content (Miah et al 2017 ). The development of deep learning models has become a popular approach to perform highly sophisticated image analytics (Shin et al 2020 ). The deep learning models can “generate generic image features in a scalable manner” that allow analysts to assess the impact of specific images on social media programs (Shin et al 2020 ).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Performing social media analytics with Brandwatch for Classrooms: a platform review

McGuirk

2021

J Market Anal

View full text Add to dashboard Cite

As consumer’s consumption of digital media and usage of social media platforms continues to grow, businesses have been searching for new ways to track, analyze, and measure this online consumer behavior to support a diverse set of business functions such as marketing, customer support, and customer experience management. Given the heightened interest in social media analytics in the business community, educational institutions have also been interested in identifying new ways to introduce emerging social media analytics concepts and practices to their students. One category of social technologies that is specifically used to perform this type of analysis is social listening platforms. Brandwatch (recently acquired by Cision Ltd.) has created one of the leading social listening platforms. They also offer a version of this platform for educators named Brandwatch for Classrooms . This article provides an overview of the key features and capabilities of the Brandwatch for Classrooms platform, as well as numerous suggestions for incorporating the platform in marketing analytics undergraduate and graduate courses. The goal is to provide educators with practical information about social media analytics and guidance on successfully integrating social listening platforms in their course design.

show abstract

“…Through deep learning framework, visual data in social media can be applied to analyze firms and relevant strategies, e.g. social media popularity prediction, ad effectiveness in social media (Shin et al, 2020) and brand attitude analysis (Liu et al, 2020). Visual information may affect user behavior.…”

Section: Multimodal Social Media Informationmentioning

confidence: 99%

Exploring the influence of multimodal social media data on stock performance: an empirical perspective and analysis

Yuan

Tang

et al. 2021

INTR

View full text Add to dashboard Cite

PurposeDespite the extensive academic interest in social media sentiment for financial fields, multimodal data in the stock market has been neglected. The purpose of this paper is to explore the influence of multimodal social media data on stock performance, and investigate the underlying mechanism of two forms of social media data, i.e. text and pictures.Design/methodology/approachThis research employs panel vector autoregressive models to quantify the effect of the sentiment derived from two modalities in social media, i.e. text information and picture information. Through the models, the authors examine the short-term and long-term associations between social media sentiment and stock performance, measured by three metrics. Specifically, the authors design an enhanced sentiment analysis method, integrating random walk and word embeddings through Global Vectors for Word Representation (GloVe), to construct a domain-specific lexicon and apply it to textual sentiment analysis. Secondly, the authors exploit a deep learning framework based on convolutional neural networks to analyze the sentiment in picture data.FindingsThe empirical results derived from vector autoregressive models reveal that both measures of the sentiment extracted from textual information and pictorial information in social media are significant leading indicators of stock performance. Moreover, pictorial information and textual information have similar relationships with stock performance.Originality/valueTo the best of the authors’ knowledge, this is the first study that incorporates multimodal social media data for sentiment analysis, which is valuable in understanding pictures of social media data. The study offers significant implications for researchers and practitioners. This research informs researchers on the attention of multimodal social media data. The study’s findings provide some managerial recommendations, e.g. watching not only words but also pictures in social media.

show abstract

Enhancing Social Media Analysis with Visual Data Analytics: A Deep Learning Approach

Cited by 115 publications

References 0 publications

Deep Visual Analytics (DVA): Applications, Challenges and Future Directions

Deep Visual Analytics (DVA): Applications, Challenges and Future Directions

Performing social media analytics with Brandwatch for Classrooms: a platform review

Exploring the influence of multimodal social media data on stock performance: an empirical perspective and analysis

Contact Info

Product

Resources

About