Abstract. Biological knowledge is increasingly represented as a collection of (entity-relationship-entity) triplets. These are queried, mined, appended to papers, and published. However, this representation ignores the argumentation contained within a paper and the relationships between hypotheses, claims and evidence put forth in the article. In this paper, we propose an alternate view of the research article as a network of ‘hypotheses and evidence’. Our knowledge representation focuses on scientific discourse as a rhetorical activity, which leads to a different direction in the development of tools and processes for modeling this discourse. We propose to extract knowledge from the article to allow the construction of a system where a specific scientific claim is connected, through trails of meaningful relationships, to experimental evidence. We discuss some current efforts and future plans in this area.

Analysis of political communication is an important aspect of political research. Thematic content analysis has yielded considerable success both with manual and automatic coding, but Semantic Network Analysis has proven more difficult, both for humans and for the computer. This article presents a system for an automated Semantic Network Analysis of Dutch texts. The system automatically extracts relations between political actors based on the output of syntactic analysis of Dutch newspaper articles. Specifically, the system uses pattern matching to find source constructions and determine the semantic agent and patient of relations, and name matching and anaphora resolution to identify political actors. The performance of the system is judged by comparing the extracted relations to manual codings of the same material. Results on the level of measurement indicate acceptable performance. We also estimate performance at the levels of analysis by using a case study of media authority, resulting in good correlations between the theoretical variables derived from the automatic and manual analysis. Finally, we test a number of substantive hypo-theses with regression models using the automatic and manual output, resulting in highly similar models in each case. This suggests that our method has sufficient performance to be used to answer relevant political questions in a valid way. 1

We explore the application of supervised machine learning (SML) to frame coding. By automating the coding of frames in news, SML facilitates the incorporation of large-scale content analysis into framing research, even if financial resources are scarce. This furthers a more integrated investigation of framing processes conceptually as well as methodologically. We conduct several experiments in which we automate the coding of four generic frames that are operationalised as a set of indicator questions. In doing so, we compare two approaches to modelling the coherence between indicator questions and frames as an SML task. The results of our experiments show that SML is well suited to automate frame coding but that coding performance is dependent on the way SML is implemented. In most framing studies, news frames are coded with indicator questions in manual Content Analysis (CA) (Matthes, 2009). Generally, measures of several indicators are combined to cover different aspects of a frame (e.g., Simon & Xenos, 2000). Human coders can be properly trained to code frame indicators, and through training their performance can be improved until accu-racy and reliability reach satisfactory levels. However, human coding is a time-consuming and costly process. This limits the scope of CA in framing research. Computers, in contrast, are more naturally suited for the processing of large quantities of documents and the repetitiveness of cod-

Part of the Artificial Intelligence and Robotics Commons This Conference Paper is brought to you for free and open access by the Digital Media Centre at

Analysis of political communication is an important aspect of political research. Thematic content analysis has yielded considerable success both with manual and automatic coding, but Semantic Network Analysis has proven more difficult, both for humans and for the computer. This article presents a system for an automated Semantic Network Analysis of Dutch texts. The system automatically extracts relations between political actors based on the output of syntactic analysis of Dutch newspaper articles. Specifically, the system uses pattern matching to find source constructions and determine the semantic agent and patient of relations, and name matching and anaphora resolution to identify political actors. The performance of the system is judged by comparing the extracted relations to manual codings of the same material. Results on the level of measurement indicate acceptable performance. We also estimate performance at the levels of analysis by using a case study of media authority, resulting in good correlations between the theoretical variables derived from the automatic and manual analysis. Finally, we test a number of substantive hypotheses with regression models using the automatic and manual output, resulting in highly similar models in each case. This suggests that our method has sufficient performance to be used to answer relevant political questions in a valid way. 1

From sentiments and opinions in texts to positions of political parties

and other research outputs

www.mdpi.com/journal/energies