This paper introduces the NewYeS corpus, which contains the Christmas messages and New Year’s speeches held at the end of the year by the heads of state of different European countries (namely Denmark, France, Italy, Norway, Spain and the United Kingdom). The corpus was collected via web scraping of the speech transcripts available online. A comparative analysis was conducted to examine some of the cultural differences showing through the texts, namely a frequency distribution analysis of the term “God” and the identification of the three most frequent content words per year, with a focus on years in which significant historical events happened. An analysis of positive and negative emotion scores, examined along with the frequency of religious references, was carried out for those countries whose languages are supported by LIWC, a tool for sentiment analysis. The corpus is available for further analyses, both comparative (across countries) and diachronic (over the years).
Twitter has been used as a textual resource to attempt to predict the outcome of elections for over a decade. A body of literature suggests that this is not consistently possible. In this paper we test the hypothesis that mentions of political parties in tweets are better correlated with the appearance of party names in newspapers than to the intention of the tweeter to vote for that party. Five Dutch national elections are used in this study. We find only a small positive, negligible difference in Pearson’s correlation coefficient as well as in the absolute error of the relation between tweets and news, and between tweets and elections. However, we find a larger correlation and a smaller absolute error between party mentions in newspapers and the outcome of the elections in four of the five elections. This suggests that newspapers are a better starting point for predicting the election outcome than tweets.
We present a new dataset of online debates in English, annotated with stance. The dataset was scraped from the “Debating Europe” platform, where users exchange opinions over different subjects related to the European Union. The dataset is composed of 2600 comments pertaining to 18 debates related to the “European Green Deal”, in a conversational setting. After presenting the dataset and the annotated sub-part, we pre-train a model for a multilingual stance classification over the X-stance dataset before fine-tuning it over our dataset, and vice-versa. The fine-tuned models are shown to improve stance classification performance on each of the datasets, even though they have different languages, topics and targets. Subsequently, we propose to enhance the performances over “Debating Europe” with an interaction-aware model, taking advantage of the online debate structure of the platform. We also propose a semi-supervised self-training method to take advantage of the imbalanced and unlabeled data from the whole website, leading to a final improvement of accuracy by 3.4% over a Vanilla XLM-R model.
Media framing refers to highlighting certain aspect of an issue in the news to promote a particular interpretation to the audience. Supervised learning has often been used to recognize frames in news articles, requiring a known pool of frames for a particular issue, which must be identified by communication researchers through thorough manual content analysis. In this work, we devise an unsupervised learning approach to discover the frames in news articles automatically. Given a set of news articles for a given issue, e.g., gun violence, our method first extracts frame elements from these articles using related Wikipedia articles and the Wikipedia category system. It then uses a community detection approach to identify frames from these frame elements. We discuss the effectiveness of our approach by comparing the frames it generates in an unsupervised manner to the domain-expert-derived frames for the issue of gun violence, for which a supervised learning model for frame recognition exists.
The popularity of social media makes politicians use it for political advertisement. Therefore, social media is full of electoral agitation (electioneering), especially during the election campaigns. The election administration cannot track the spread and quantity of messages that count as agitation under the election code. It addresses a crucial problem, while also uncovering a niche that has not been effectively targeted so far. Hence, we present the first publicly open data set for detecting electoral agitation in the Polish language. It contains 6,112 human-annotated tweets tagged with four legally conditioned categories. We achieved a 0.66 inter-annotator agreement (Cohen’s kappa score). An additional annotator resolved the mismatches between the first two improving the consistency and complexity of the annotation process. The newly created data set was used to fine-tune a Polish Language Model called HerBERT (achieving a 68% F1 score). We also present a number of potential use cases for such data sets and models, enriching the paper with an analysis of the Polish 2020 Presidential Election on Twitter.
Unstructured text documents such as news and blogs often present references to places. Those references, called toponyms, can be used in various applications like disaster warning and touristic planning. However, obtaining the correct coordinates for toponyms, called geocoding, is not easy since it’s common for places to have the same name as other locations. The process becomes even more challenging when toponyms appear in adjectival form, as they are different from the place’s actual name. This paper addresses the geocoding task and aims to improve, through a heuristic approach, the process for adjectival toponyms. So first, a baseline geocoder is defined through experimenting with a set of heuristics. After that, the baseline is enhanced by adding a normalization step to map adjectival toponyms to their noun form at the beginning of the geocoding process. The results show improved performance for the enhanced geocoder compared to the baseline and other geocoders.
Causality detection is the task of extracting information about causal relations from text. It is an important task for different types of document analysis, including political impact assessment. We present two new data sets for causality detection in Swedish. The first data set is annotated with binary relevance judgments, indicating whether a sentence contains causality information or not. In the second data set, sentence pairs are ranked for relevance with respect to a causality query, containing a specific hypothesized cause and/or effect. Both data sets are carefully curated and mainly intended for use as test data. We describe the data sets and their annotation, including detailed annotation guidelines. In addition, we present pilot experiments on cross-lingual zero-shot and few-shot causality detection, using training data from English and German.
Every day, the world is flooded by millions of messages and statements posted on Twitter or Facebook. Social media platforms try to protect users’ personal data, but there still is a real risk of misuse, including elections manipulation. Did you know, that only 10 posts addressing important or controversial topics for society are enough to predict one’s political affiliation with a 0.85 F1-score? To examine this phenomenon, we created a novel universal method of semi-automated political leaning discovery. It relies on a heuristical data annotation procedure, which was evaluated to achieve 0.95 agreement with human annotators (counted as an accuracy metric). We also present POLiTweets - the first publicly open Polish dataset for political affiliation discovery in a multi-party setup, consisting of over 147k tweets from almost 10k Polish-writing users annotated heuristically and almost 40k tweets from 166 users annotated manually as a test set. We used our data to study the aspects of domain shift in the context of topics and the type of content writers - ordinary citizens vs. professional politicians.
With the significant increase in users on social media platforms, a new means of political campaigning has appeared. Twitter and Facebook are now notable campaigning tools during elections. Indeed, the candidates and their parties now take to the internet to interact and spread their ideas. In this paper, we aim to identify political communities formed on Twitter during the 2022 French presidential election and analyze each respective community. We create a large-scale Twitter dataset containing 1.2 million users and 62.6 million tweets that mention keywords relevant to the election. We perform community detection on a retweet graph of users and propose an in-depth analysis of the stance of each community. Finally, we attempt to detect offensive tweets and automatic bots, comparing across communities in order to gain insight into each candidate’s supporter demographics and online campaign strategy.
The TCPD-IPD dataset is a collection of questions and answers discussed in the Lower House of the Parliament of India during the Question Hour between 1999 and 2019. Although it is difficult to analyze such a huge collection manually, modern text analysis tools can provide a powerful means to navigate it. In this paper, we perform an exploratory analysis of the dataset. In particular, we present insightful corpus-level statistics and perform a more detailed analysis of three subsets of the dataset. In the latter analysis, the focus is on understanding the temporal evolution of topics using a dynamic topic model. We observe that the parliamentary conversation indeed mirrors the political and socio-economic tensions of each period.
Don’t Burst Blindly: For a Better Use of Natural Language Processing to Fight Opinion Bubbles in News Recommendations
Evan Dufraisse | Célina Treuillier | Armelle Brun | Julien Tourille | Sylvain Castagnos | Adrian Popescu
Online news consumption plays an important role in shaping the political opinions of citizens. The news is often served by recommendation algorithms, which adapt content to users’ preferences. Such algorithms can lead to political polarization as the societal effects of the recommended content and recommendation design are disregarded. We posit that biases appear, at least in part, due to a weak entanglement between natural language processing and recommender systems, both processes yet at work in the diffusion and personalization of online information. We assume that both diversity and acceptability of recommended content would benefit from such a synergy. We discuss the limitations of current approaches as well as promising leads of opinion-mining integration for the political news recommendation process.
In this paper we describe a Polish news corpus as an attempt to create a filtered, organized and representative set of texts coming from contemporary online press articles from two major Polish TV news providers: commercial TVN24 and state-owned TVP Info. The process consists of web scraping, data cleaning and formatting. A random sample was selected from prepared data to perform a classification task. The random forest achieved the best prediction results out of all considered models. We believe that this dataset is a valuable contribution to existing Polish language corpora as online news are considered to be formal and relatively mistake-free, therefore, a reliable source of correct written language, unlike other online platforms such as blogs or social media. Furthermore, to our knowledge, such corpus from this period of time has not been created before. In the future we would like to expand this dataset with articles coming from other online news providers, repeat the classification task on a bigger scale, utilizing other algorithms. Our data analysis outcomes might be a relevant basis to improve research on a political polarization and propaganda techniques in media.
We present a French corpus of political interviews labeled at the utterance level according to expressive dimensions such as Arousal. This corpus consists of 7.5 hours of high-quality audio-visual recordings with transcription. At the time of this publication, 1 hour of speech was segmented into short utterances, each manually annotated in Arousal. Our segmentation approach differs from similar corpora and allows us to perform an automatic Arousal prediction baseline by building a speech-based classification model. Although this paper focuses on the acoustic expression of Arousal, it paves the way for future work on conflictual and hostile expression recognition as well as multimodal architectures.
Sarcasm is extensively used in User Generated Content (UGC) in order to express one’s discontent, especially through blogs, forums, or social media such as Twitter. Several works have attempted to detect and analyse sarcasm in UGC. However, the lack of freely available corpora in this field makes the task even more difficult. In this work, we present “TransCasm” corpus, a parallel corpus of sarcastic tweets translated from English into French along with their non-sarcastic representations. To build the bilingual corpus of sarcasm, we select the “SIGN” corpus, a monolingual data set of sarcastic tweets and their non-sarcastic interpretations, created by (Peled and Reichart, 2017). We propose to define linguistic guidelines for developing “TransCasm” which is the first ever bilingual corpus of sarcastic tweets. In addition, we utilise “TransCasm” for building a binary sarcasm classifier in order to identify whether a tweet is sarcastic or not. Our experiment reveals that the sarcasm classifier achieves 61% accuracy on detecting sarcasm in tweets. “TransCasm” is now freely available online and is ready to be explored for further research.