Stance Categories Research Articles

Rethinking citations: proposing a new model for analyzing stance and rhetorical functions of citations in interdisciplinary discourse

ABSTRACT The current study investigates citation practices in publications published in the journal Global Environmental Change. Twenty papers were selected to cover the period from 1990 to 2010. The model was applied to the selected papers, which included hundreds of in-block citations, to identify categories at different levels and compare clause- and block-level findings for each citation. The proposed model is considered a triangular system that integrates as well as aligns the chosen categories of the functions, stance, and form of citation. A comparison between the block-level analysis of citation functions and the clause-level analysis of stance categories demonstrates how citations work and their role in citation texts. By combining functional categories and stance, we gain an understanding of both conventional and unconventional patterns of citation. The article argues that starting with the block-level analysis, as a recently discovered level of analysis, is most useful for understanding students’ awareness of the block and how it affects the execution of citation practices by researchers or writers—specifically, the position of each citation. The suggested system can be extended to interdisciplinary discourse to investigate heterogeneity in citation practices.

Knowledge-enhanced Prompt-tuning for Stance Detection

Investigating public attitudes on social media is important in opinion mining systems. Stance detection aims to analyze the attitude of an opinionated text (e.g., favor, neutral, or against) toward a given target. Existing methods mainly address this problem from the perspective of fine-tuning. Recently, prompt-tuning has achieved success in natural language processing tasks. However, conducting prompt-tuning methods for stance detection in real-world remains a challenge for several reasons: (1) The text form of stance detection is usually short and informal, which makes it difficult to design label words for the verbalizer. (2) The tweet text may not explicitly give the attitude. Instead, users may use various hashtags or background knowledge to express stance-aware perspectives. In this article, we first propose a prompt-tuning-based framework that performs stance detection in a cloze question manner. Specifically, a knowledge-enhanced prompt-tuning framework (KEprompt) method is designed, which consists of an automatic verbalizer (AutoV) and background knowledge injection (BKI). Specifically, in AutoV, we introduce a semantic graph to build a better mapping from the predicted word of the pretrained language model and detection labels. In BKI, we first propose a topic model for learning hashtag representation and introduce ConceptGraph as the supplement of the target. At last, we present a challenging dataset for stance detection, where all stance categories are expressed in an implicit manner. Extensive experiments on a large real-world dataset demonstrate the superiority of KEprompt over state-of-the-art methods.

Evaluating stance annotation of Twitter data

Taking stance towards any topic, event or idea is a common phenomenon on Twitter and social media in general. Twitter users express their opinions about different matters and assess other people’s opinions in various discursive ways. The identification and analysis of the linguistic ways that people use to take different stances leads to a better understanding of the language and user behaviour on Twitter. Stance is a multidimensional concept involving a broad range of related notions such as modality, evaluation and sentiment. In this study, we annotate data from Twitter using six notional stance categories ––contrariety, hypotheticality, necessity, prediction, source of knowledge and uncertainty––¬¬ following a comprehensive annotation protocol including inter-coder reliability measurements. The relatively low agreement between annotators highlighted the challenges that the task entailed, which made us question the inter-annotator agreement score as a reliable measurement of annotation quality of notional categories. The nature of the data, the difficulty of the stance annotation task and the type of stance categories are discussed, and potential solutions are suggested

HeadlineStanceChecker: Exploiting summarization to detect headline disinformation

The headline of a news article is designed to succinctly summarize its content, providing the reader with a clear understanding of the news item. Unfortunately, in the post-truth era, headlines are more focused on attracting the reader’s attention for ideological or commercial reasons, thus leading to mis- or disinformation through false or distorted headlines. One way of combating this, although a challenging task, is by determining the relation between the headline and the body text to establish the stance. Hence, to contribute to the detection of mis- and disinformation, this paper proposes an approach (HeadlineStanceChecker) that determines the stance of a headline with respect to the body text to which it is associated. The novelty rests on the use of a two-stage classification architecture that uses summarization techniques to shape the input for both classifiers instead of directly passing the full news body text, thereby reducing the amount of information to be processed while keeping important information. Specifically, summarization is done through Positional Language Models leveraging on semantic resources to identify salient information in the body text that is then compared to its corresponding headline. The results obtained show that our approach achieves 94.31% accuracy for the overall classification and the best FNC-1 relative score compared with the state of the art. It is especially remarkable that the system, which uses only the relevant information provided by the automatic summaries instead of the whole text, is able to classify the different stance categories with very competitive results, especially in the discuss stance between the headline and the news body text. It can be concluded that using automatic extractive summaries as input of our approach together with the two-stage architecture is an appropriate solution to the problem.

A two-step procedure to identify lexical elements of stance constructions in discourse from political blogs

The Brexit Blog Corpus (bbc) is a collection of texts extracted from political blogs, which, in a recent study, was annotated according to a cognitive–functional stance framework by two independent annotators (Annotator A and B) using semantic criteria ( Simaki et al., 2017 ). The goal was to label the stance or stances taken based on the overall meaning of a set of utterances. The annotators were not instructed to identify the lexical forms that were used to express the stances. In this study, we make use of those stance-labelled utterances as a springboard to approach stance-taking in text from the opposite point of view, namely from how stance is realised through language. Our aim is to provide a description of the specific lexical elements used to express six stance categories (i.e., contrariety, hypotheticality, necessity, prediction, source of knowledge and uncertainty). To this end, we followed a two-step experimental procedure. First, we performed a quantitative analysis of the stance-labelled utterances in order to identify the lexical realisations of each stance category. Second, we carried out a meta-annotation of the data. Annotator B was instructed to single out the actual lexical forms of the constructions that triggered his semantic stance category decisions. This meta-annotation procedure made it possible for us to sift out the most salient lexical realisations of the constructions of each of the six category types on the basis of the qualitative assessments made by Annotator B. We then compared the results of the quantitative and the qualitative approaches, and we present a list of shared stance expressions for each stance category type.

Evaluating stance-annotated sentences from the Brexit Blog Corpus: A quantitative linguistic analysis

AbstractThis paper offers a formally driven quantitative analysis of stance-annotated sentences in the Brexit Blog Corpus (BBC). Our goal is to identify features that determine the formal profiles of six stance categories (contrariety, hypotheticality, necessity, prediction, source of knowledgeanduncertainty) in a subset of the BBC. The study has two parts: firstly, it examines a large number of formal linguistic features, such as punctuation, words and grammatical categories 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 stance similarities in the data set. We show that among the six stance categories in the corpus,contrarietyandnecessityare the most discriminative ones, with the former using longer sentences, more conjunctions, more repetitions and shorter forms than the sentences expressing other stances.necessityhas 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.

Annotating Speaker Stance in Discourse: The Brexit Blog Corpus

AbstractThe aim of this study is to explore the possibility of identifying speaker stance in discourse, provide an analytical resource for it and an evaluation of the level of agreement across speakers. We also explore to what extent language users agree about what kind of stances are expressed in natural language use or whether their interpretations diverge. In order to perform this task, a comprehensive cognitive-functional framework of ten stance categories was developed based on previous work on speaker stance in the literature. A corpus of opinionated texts was compiled, the Brexit Blog Corpus (BBC). An analytical protocol and interface (Active Learning and Visual Analytics) for the annotations was set up and the data were independently annotated by two annotators. The annotation procedure, the annotation agreements and the co-occurrence of more than one stance in the utterances are described and discussed. The careful, analytical annotation process has returned satisfactory inter- and intra-annotation agreement scores, resulting in a gold standard corpus, the final version of the BBC.

Active Learning and Visual Analytics for Stance Classification with ALVA

The automatic detection and classification of stance (e.g., certainty or agreement) in text data using natural language processing and machine-learning methods creates an opportunity to gain insight into the speakers’ attitudes toward their own and other people’s utterances. However, identifying stance in text presents many challenges related to training data collection and classifier training. To facilitate the entire process of training a stance classifier, we propose a visual analytics approach, called ALVA, for text data annotation and visualization. ALVA’s interplay with the stance classifier follows an active learning strategy to select suitable candidate utterances for manual annotaion. Our approach supports annotation process management and provides the annotators with a clean user interface for labeling utterances with multiple stance categories. ALVA also contains a visualization method to help analysts of the annotation and training process gain a better understanding of the categories used by the annotators. The visualization uses a novel visual representation, called CatCombos, which groups individual annotation items by the combination of stance categories. Additionally, our system makes a visualization of a vector space model available that is itself based on utterances. ALVA is already being used by our domain experts in linguistics and computational linguistics to improve the understanding of stance phenomena and to build a stance classifier for applications such as social media monitoring.

Visual analysis of online social media to open up the investigation of stance phenomena.

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.

Sex similarities and differences in stance in informal American conversation1

This study compares men's and women's use of stance: the expression of attitude, emotion, certainty, doubt and commitment. A corpus of nearly 900,000 words of informal conversation in social and work contexts was examined with a computer program that measured stance. The main categories, subcategories and the 180 most frequent stance expressions were analyzed with multiple ANOVAs. The main stance categories of affect, evidentials, and quantifiers showed no significant differences between men and women. In terms of subcategories, general affect, boulomaic verbs, general evidentials, mental verbs, hedges and emphatics had no significant differences between men and women; only expletives had a significant difference between men and women. Of the individual stance expressions, only 35 showed a significant difference between men and women. Examples from actual conversations are given to compare men's and women's speech. Cooperative work between qualitative and quantitative researchers is recommended.