Philipp Heinrich

Friedrich-Alexander-University of Erlangen-Nürnberg | FAU · Department of German and Comparative Studies

Disadvantage and privilege work together to uphold systems of inequality. Nevertheless, racial inequality is often described as Black disadvantage, while White privilege remains less visible. This one-sided framing in public discourse may result in equally one-sided understandings of and policies aimed at reducing inequality. In the present researc...

Twitter sentiment analysis, which often focuses on predicting the polarity of tweets, has attracted increasing attention over the last years, in particular with the rise of deep learning (DL). In this paper, we propose a new task: predicting the predominant sentiment among (first-order) replies to a given tweet. Therefore, we created RETWEET, a lar...

Twitter sentiment analysis, which often focuses on predicting the polarity of tweets, has attracted increasing attention over the last years, in particular with the rise of deep learning (DL). In this paper, we propose a new task: predicting the predominant sentiment among (first-order) replies to a given tweet. Therefore, we created RETWEET, a lar...

We present an approach to extracting arguments from social media, exemplified by a case study on a large corpus of Twitter messages collected under the #Brexit hashtag during the run-up to the referendum in 2016. Our method is based on constructing dedicated corpus queries that capture predefined argumentation patterns following standard Walton-sty...

Der Weg zurück zur Kontrolle über die eigene Souveränität und Freiheit begann für Großbritannien mit einem Referendum gegen den Verbleib in der Europäischen Union im Juni 2016 sowie dem offiziellen Austrittsantrag im Juni 2017. Als Direktverbindung in die Unabhängigkeit propagiert, entpuppte sich der Weg schnell als mäandernder Pfad gespickt mit in...

Social media are of paramount importance to public discourse. RANT aims to contribute methods and formalisms for extracting, representing, and processing arguments from noisy text found in social media discussions, using a large corpus of pre-referendum Brexit tweets as a running case study. We identify recurring linguistic argumentation patterns i...

Austerity cannot be reduced to spending cuts but has to be understood as a complex social phenomenon. As social reality is always mediated, media play a central role within the struggle between different evaluations and constructions of austerity. This edited volume is based on a workshop that took place in September 2017 in Erlangen and that broug...

Based on a comparison of a small subset of the austerity corpus for texts that also contain the search term Brexit with a corpus of tweets that include austerity and Brexit as well, this chapter offers an explanatory critique of the cultural political economy of Brexit in the age of austerity with the help of a corpus-assisted critical realist mult...

Im Anbetracht der Debatte über die Relevanz und ausgehende Gefahr von Social Bots im politischen Kontext wurde untersucht, ob es eine nennenswerte Aktivität automatisierter Twitter-Accounts im Zusammenhang mit der Europawahl 2019 gab. Die Analyse bezieht sich auf deutsch- und englischsprachige Tweets aus der heißen Phase des Europawahlkampfs und nu...

We investigate an approach to improving statistical text classification by combining machine learners with an ontology-based identification of domain-specific topic categories. We apply this approach to ad hoc disclosures by public companies. This form of obligatory publicity concerns all information that might affect the stock price; relevant topi...

Im Oktober 2016 – lange vor Beginn des Bundeswahlkampfes – appellierte Bundeskanzlerin Angela Merkel an alle Parteien, auf die Nutzung von Social Bots im Bundestagswahlkampf zu verzichten. Dem widersprach letztendlich nur die Alternative für Deutschland [AfD], wenngleich die Partei diese Aussage später wieder relativierte. So widmet sich dieser Bei...

Although the form of linguistic articulations in both mass and social media is central to understanding the construction of the nexus of austerity and Brexit, something else must be brought into the picture to understand their force. From the perspective of Cultural Political Economy this something else has to be located in material social structur...

In this article, we present results on the identification and behavioral analysis of social bots in a sample of 542,584 Tweets, collected before and after Japan's 2014 general election. Typical forms of bot activity include massive Retweeting and repeated posting of (nearly) the same message, sometimes used in combination. We focus on the second me...