| 1. |
|
|
| 2. |
- Kucher, Kostiantyn, 1989-
(författare)
-
Sentiment and Stance Visualization of Textual Data for Social Media
- 2019
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Rapid progress in digital technologies has transformed the world in many ways during the past few decades, in particular, with the new means of communication such as social media. Social media platforms typically rely on textual data produced or shared by the users in multiple timestamped posts. Analyses of such data are challenging for traditional manual methods that are unable to scale up to the volume and the variety of the data. While computational methods can partially address these challenges, they have to be used together with the methods developed within information visualization and visual analytics to gain knowledge from the text data by using interactive visual representations.One of the most interesting aspects of text data is related to expressions of sentiments and opinions. The corresponding task of sentiment analysis has been studied within computational linguistics, and sentiment visualization techniques exist as well. However, there are gaps in research on the related task of stance analysis, dedicated to subjectivity that is not expressible only in terms of sentiment. Research on stance is an area of interest in linguistics, but support by computational and visual methods has been limited so far. The challenges related to definition, analysis, and visualization of stance in textual data call for an interdisciplinary research effort. The StaViCTA project addressed these challenges with a focus on written text in English. The corresponding results in the area of visualization are reported in this work, based on multiple publications.The main goal of this dissertation is to define, categorize, and implement means for visual analysis of sentiment and stance in textual data, in particular, for social media. Our work is based on the theoretical framework and automatic classifier of stance developed by our project collaborators, involving multiple non-exclusive stance categories such as certainty and prediction. We define a design space for sentiment and stance visualization techniques based on literature surveys. We discuss multiple visualization and visual analytics approaches developed by us to facilitate the underlying research on stance analysis, data collection and annotation, and visual analysis of sentiment and stance in real-world text data from several social media sources. The work described in this dissertation was carried out in cooperation with domain experts in linguistics and computational linguistics, and our approaches were validated with case studies, expert user reviews, and critical discussion. The results of this work open up further opportunities for research in text visualization and visual text analytics. The potential application areas are academic research, business intelligence, social media monitoring, and journalism.
|
|
| 3. |
- Kucher, Kostiantyn, et al.
(författare)
-
Visual Analysis of Online Social Media to Open Up the Investigation of Stance Phenomena
- 2016
-
Ingår i: Information Visualization. - : Sage Publications. - 1473-8716 .- 1473-8724. ; 15:2, s. 93-116
-
Tidskriftsartikel (refereegranskat)abstract
- Online social media are a perfect text source for stance analysis. Stance in human communication is concerned with speaker attitudes, beliefs, feelings and opinions. Expressions of stance are associated with the speakers' view of what they are talking about and what is up for discussion and negotiation in the intersubjective exchange. Taking stance is thus crucial for the social construction of meaning. Increased knowledge of stance can be useful for many application fields such as business intelligence, security analytics, or social media monitoring. In order to process large amounts of text data for stance analyses, linguists need interactive tools to explore the textual sources as well as the processed data based on computational linguistics techniques. Both original texts and derived data are important for refining the analyses iteratively. In this work, we present a visual analytics tool for online social media text data that can be used to open up the investigation of stance phenomena. Our approach complements traditional linguistic analysis techniques and is based on the analysis of utterances associated with two stance categories: sentiment and certainty. Our contributions include (1) the description of a novel web-based solution for analyzing the use and patterns of stance meanings and expressions in human communication over time; and (2) specialized techniques used for visualizing analysis provenance and corpus overview/navigation. We demonstrate our approach by means of text media on a highly controversial scandal with regard to expressions of anger and provide an expert review from linguists who have been using our tool.
|
|
| 4. |
|
|
| 5. |
|
|
| 6. |
- Simaki, Vasiliki, et al.
(författare)
-
Evaluating stance-annotated sentences from the Brexit Blog Corpus : A quantitative linguistic analysis
- 2018
-
Ingår i: ICAME Journal/International Computer Archive of Modern English. - : De Gruyter Open. - 0801-5775 .- 1502-5462. ; 42:1, s. 133-166
-
Tidskriftsartikel (refereegranskat)abstract
- This paper offers a formally driven quantitative analysis of stance-annotated sentences in the Brexit Blog Corpus (BBC). Our goal is to highlight linguistic features that determine the formal profiles of six stance categories (contrariety, hypotheticality, necessity, prediction, source of knowledge and uncertainty) in a subset of the BBC. The study has two parts: firstly, it examines a large number of formal linguistic features that occur in the sentences in order to describe the specific characteristics of each category, and secondly, it compares characteristics in the entire data set in order to determine linguistic similarities throughout the data set. We show that among the six stance categories in the corpus, contrariety and necessity are the most discriminative ones, with the former using longer sentences, more conjunctions, more repetitions and shorter forms than the sentences expressing other stances. The latter has longer lexical forms but shorter sentences, which are syntactically more complex. We show that stance in our data set is expressed in sentences with around 21 words per sentence. The sentences consist mainly of alphabetical characters forming a varied vocabulary without special forms, such as digits or special characters.
|
|
