Abstract
Text visualization and visual text analytics methods have been successfully applied for various tasks related to the analysis of individual text documents and large document collections such as summarization of main topics or identification of events in discourse. Visualization of sentiments and emotions detected in textual data has also become an important topic of interest, especially with regard to the data originating from social media. Despite the growing interest in this topic, the research problem related to detecting and visualizing various stances, such as rudeness or uncertainty, has not been adequately addressed by the existing approaches. The challenges associated with this problem include the development of the underlying computational methods and visualization of the corresponding multi-label stance classification results. In this paper, we describe our work on a visual analytics platform, called StanceVis Prime, which has been designed for the analysis of sentiment and stance in temporal text data from various social media data sources. The use case scenarios intended for StanceVis Prime include social media monitoring and research in sociolinguistics. The design was motivated by the requirements of collaborating domain experts in linguistics as part of a larger research project on stance analysis. Our approach involves consuming documents from several text stream sources and applying sentiment and stance classification, resulting in multiple data series associated with source texts. StanceVis Prime provides the end users with an overview of similarities between the data series based on dynamic time warping analysis, as well as detailed visualizations of data series values. Users can also retrieve and conduct both distant and close reading of the documents corresponding to the data series. We demonstrate our approach with case studies involving political targets of interest and several social media data sources and report preliminary user feedback received from a domain expert.Graphic abstract
Highlights
The recent years have demonstrated how massively available digital communication channels, such as social media, affect world politics and shape the agenda in multiple spheres of life
We describe our work on a visual analytics platform, called StanceVis Prime, which has been designed for the analysis of sentiment and stance in temporal text data from various social media data sources
Text visualization (Kucher and Kerren 2015) and visual text analytics (Liu et al 2019) methods can support various tasks related to the analysis of individual text documents and large document collections such as summarization of main topics or identification of events in discourse (Dou and Liu 2016), using the techniques developed for timeoriented data visualization (Aigner et al 2011), when necessary
Summary
The recent years have demonstrated how massively available digital communication channels, such as social media, affect world politics and shape the agenda in multiple spheres of life. Some of the most interesting aspects of human communication to analyze in such data are related to various expressions of subjectivity in social media document texts, such as sentiments, opinions, and emotions (Pang and Lee 2008; Mohammad 2016; Zhang et al 2018). The analysis of stance-taking in texts (Englebretson 2007) can provide even further insights about the subjective position of the speaker, for instance, AGREEMENT or DISAGREEMENT with a certain topic (Chen and Ku 2016; Mohammad et al 2016, 2017), or expression of CERTAINTY and PREDICTION (Simaki et al 2017). The existing surveys (Pang and Lee 2008; Mohammad 2016; Zhang et al 2018) describe a multitude of existing approaches for sentiment classification at various levels of granularity, from words to complete documents, and with various categories, from POSITIVE/NEUTRAL/NEGATIVE to multidimensional emotion models. Our approach is not specific to VADER, though, and could use a better performing deep learning classifier (Lai et al 2015; Zhang et al 2018) in the future to achieve better classification quality/performance
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
