Suchergebnisse

AbstractSentiment analysis techniques have a long history in natural language processing and have become a standard tool in the analysis of political texts, promising a conceptually straightforward automated method of extracting meaning from textual data by scoring documents on a scale from positive to negative. However, while these kinds of sentiment scores can capture the overall tone of a document, the underlying concept of interest for political analysis is often actually the document's stance with respect to a given target—how positively or negatively it frames a specific idea, individual, or group—as this reflects the author's underlying political attitudes. In this paper, we question the validity of approximating author stance through sentiment scoring in the analysis of political texts, and advocate for greater attention to be paid to the conceptual distinction between a document's sentiment and its stance. Using examples from open-ended survey responses and from political discussions on social media, we demonstrate that in many political text analysis applications, sentiment and stance do not necessarily align, and therefore sentiment analysis methods fail to reliably capture ground-truth document stance, amplifying noise in the data and leading to faulty conclusions.

Intro -- Table of Contents -- Table of Tables -- Table of Figures -- Introduction -- 1 The Positioning of Post-Truth Politics: Claims and Evidence in the 2016 US Presidential Debates -- 2 Positioning in the Peace Process: The Colombian Peace Dialogues -- 3 Oh, That's Just Crazy Talk: How Leaders Use Language to Create Perceptions of Irrationality -- 4 Trump vs. Clinton: Implicatures as Public Stance Acts -- 5 Discarding Proper Names as Referring Expression Tweets in the Trump vs. Hillary Debate -- 6 Stance in Casting the Identity of a New Political Leader: Interviews with the President of Argentina -- 7 Epistemic and Effective Stance in Political Discourse: Th European Refugee Crisis -- Index.

This paper aims to analyse video press reviews, which are digital press videos that are composed of several video quotations. Although the quotations originate from different media sources, they are linked intertextually because they contain opinions about the same political events. The quotations contain an evaluative stance about political events. The video quotations are edited into a new media story. Although the video press review is based on the selection of journalistic content and interpretation of media material, it has novel characteristics that make it a transformed and hybrid genre. In the cases analysed, there is no explicit journalistic voice to comment on the quoted material or the quoted persons. The origin of the quotations is not identified in every case. In this sense, the video press review does not fulfil the exigencies of reliability of information. The journalistic stance consists of composing a new story that relies on the viewers' capacity to recognise the genre's similarity to social media videos and independently draw conclusions about the meaning of the news information after reviewing quoted material. ; This paper aims to analyse video press reviews, which are digital press videos that are composed of several video quotations. Although the quotations originate from different media sources, they are linked intertextually because they contain opinions about the same political events. The quotations contain an evaluative stance about political events. The video quotations are edited into a new media story. Although the video press review is based on the selection of journalistic content and interpretation of media material, it has novel characteristics that make it a transformed and hybrid genre. In the cases analysed, there is no explicit journalistic voice to comment on the quoted material or the quoted persons. The origin of the quotations is not identified in every case. In this sense, the video press review does not fulfil the exigencies of reliability of information. The journalistic stance consists of composing a new story that relies on the viewers' capacity to recognise the genre's similarity to social media videos and independently draw conclusions about the meaning of the news information after reviewing quoted material.

Taking a political stance in social work necessarily involves a close historical examination of the influence of social and economic structure as well as the constituting context of relations of domination. It also involves articulating an ontology of the political subject. We maintain that the proper conceptual space for understanding the possibility of taking a political stance is that of political ontology. In defining this space we draw on issues raised in The New Politics of Social Work (Gray and Webb, 2013) bringing together aspects of social structure and agency for radical social work. We ask against which principles a radical social work stance might be judged and question the extent to which it can be positioned as a counter-strategy to both neoliberal capitalism and mainstream social work. The article plots the implications and meaning of the 'new politics of social work' – conceived of as a 'New Social Work Left'.

Predicting users political party in social media has important impacts on many real world applications such as targeted advertising, recommendation and personalization. Several political research studies on it indicate that political parties' ideological beliefs on sociopolitical issues may influence the users political leaning. In our work, we exploit users' ideological stances on controversial issues to predict political party of online users. We propose a collaborative filtering approach to solve the data sparsity problem of users stances on ideological topics and apply clustering method to group the users with the same party. We evaluated several state-of-the-art methods for party prediction task on debate.org dataset. The experiments show that using ideological stances with Probabilistic Matrix Factorization (PMF) technique achieves a high accuracy of 88.9% at 22.9% data sparsity rate and 80.5% at 70% data sparsity rate on users' party prediction task.

[EN] Stance Detection is the task of automatically determining whether the author of a text is in favor, against, or neutral towards a given target. In this paper we investigate the portability of tools performing this task across different languages, by analyzing the results achieved by a Stance Detection system (i.e. MultiTACOS) trained and tested in a multilingual setting. First of all, a set of resources on topics related to politics for English, French, Italian, Spanish and Catalan is provided which includes: novel corpora collected for the purpose of this study, and benchmark corpora exploited in Stance Detection tasks and evaluation exercises known in literature. We focus in particular on the novel corpora by describing their development and by comparing them with the benchmarks. Second, MultiTACOS is applied with different sets of features especially designed for Stance Detection, with a specific focus to exploring and combining both features based on the textual content of the tweet (e.g., style and affective load) and features based on contextual information that do not emerge directly from the text. Finally, for better highlighting the contribution of the features that most positively affect system performance in the multilingual setting, a features analysis is provided, together with a qualitative analysis of the misclassified tweets for each of the observed languages, devoted to reflect on the open challenges. ; Cristina Bosco and Viviana Patti are partially supported by Progetto di Ateneo/CSP 2016 (Immigrants, Hate and Prejudice in Social Media, S1618_L2_BOSC_01). The work of Paolo Rosso was partially funded bythe Spanish MICINN under the research project MISMIS-FAKEnHATE on MISinformation and MIScommunication in social media: FAKE news and HATE speech (PGC2018096212-B-C31). ; Lai, M.; Cignarella, AT.; Hernandez-Farias, DI.; Bosco, C.; Patti, V.; Rosso, P. (2020). Multilingual Stance Detection in Social Media Political Debates. Computer Speech & Language. 63:1-27. ...

Abstract

This article deals with the emerging far right movements in Georgia, where the growing Europeanization process is taking place. Therefore, it aims to determine how relevant the European-experienced understanding of the far right with the similar movement political positions is. The article presents the stances of the members of far right movements (Georgian March, Anti-liberals, Georgian National Unity and Edelweiss) on foreign and identity policy and different socio-ethical issues, also assessed the neo-populist manner and belief in supremacy of the law. The conclusion summarizes the major characteristics of these far right movements in comparative way.

The language of press and television news reportage is familiar territory for critical discourse analysis and other approaches to politics in the mass media (e.g., Kelly-Holmes and O'Regan, 2004, Chouliaraki 2005), as is that of newspaper editorials (e.g. Le 2003). But, in sympathy with, e.g., van Leeuwen and Jaworski (2003), we believe that a full understanding of mediated political culture needs to extend beyond this territory to consider a wider range of linguistic, visual and multimodal media genres. This article reviews the character of political sketchwriting in Britain as a basis for an assessment of its contribution to the national political mediascape. To do this, we draw on recent work in discourse analysis (Engebretson 2007) and sociolinguistics (Jaffe 2009) on the concept of 'stance'. First, we illustrate the history of sketchwriting as a newspaper genre, tracing it back to the earliest days of political reportage in Britain. We then explore, with reference to a corpus of materials assembled during the British General Election campaign of 2010, how the stance-work of this genre is prototypically managed. Following this, we demonstrate the extension of such work to a wider range of political column discourse, under the general heading of 'colour writing'.

The article of record may be found at https://doi.org/10.1016/j.dss.2012.05.032 ; Funded by Naval Postgraduate School ; The article of record as published may be found at https://doi.org/10.1016/j.ijpe.2020.107840 ; A growing body of work has highlighted the challenges of identifying the stance that a speaker holds towards a particular topic, a task that involves identifying a holistic subjective disposition. We examine stance classification on a corpus of 4731 posts from the debate website ConvinceMe.net, for 14 topics ranging from the playful to the ideological. We show that ideological debates feature a greater share of rebuttal posts, and that rebuttal posts are significantly harder to classify for stance, for both humans and trained classifiers. We also demonstrate that the number of subjective expressions varies across debates, a fact correlated with the performance of systems sensitive to sentiment-bearing terms. We present results for classifying stance on a per topic basis that range from 60% to 75%, as compared to unigram baselines that vary between 47% and 66%. Our results suggest that features and methods that take into account the dialogic context of such posts improve accuracy. ; This work was funded by Naval Postgraduate School Grant NPS- BAA-03 to UCSC, and by the Intelligence Advanced Research Projects Activity (IARPA) through the Army Research Laboratory. ; This work was funded by Naval Postgraduate School Grant NPS- BAA-03 to UCSC, and by the Intelligence Advanced Research Projects Activity (IARPA) through the Army Research Laboratory.

This thesis investigates the strategic stance of a political brand and the factors that affect its positioning. The question related to the positioning of a political brand is complex. Nowadays, political leaders should be able to define the characteristics of their political brand. To succeed in the political arena, they must understand, identify, and utilize the most appropriate mechanism of communication to create an accurate perception of their political image in the market that is strictly linked to the characteristics of their brand and to reach these targets. For these reasons, it is mandatory to have measurement methods and comparable results over time. It was decided to divide the overall research problem into four different research questions to explore and explain the mechanism of political brand creation and the interaction between political brands and the electorate and to do so through four different papers. In paper 1, the political environment has been observed and studied. Subsequently, a theory of consumer and product orientation has been identified and utilized to both understand and to strategize how politicians can better position and present themselves to the public and voters. Paper 2 proposes a methodology to measure political positioning and constituent perception. The specific aim of the research is to explore interrelations between a political party's positioning in two different periods to discover possible discrepancies and changes over time. Paper 3 investigates whether the negative impact of a political brand can influence a country's brand. The fourth paper tried to measure how the quality, readability, and frequencies of political messages could provide insight into the effectiveness of viral communication using a political blog. This thesis contributes to the understanding that influence in a political environment happens in a bidirectional manner, where politicians are influenced by voter sentiment and voters are influenced by politicians. The key strategic question then ...