Social media house a trove of relevant information for the study of online opinion dynamics. However, harvesting and analyzing the sheer overload of data that is produced by these media poses immense challenges to journalists, researchers, activists, policy makers, and concerned citizens. To mitigate this situation, this article discusses the creation of (social) media observatories: platforms that enable users to capture the complexities of social behavior, in particular the alignment and misalignment of opinions, through computational analyses of digital media data. The article positions the concept of “observatories” for social media monitoring among ongoing methodological developments in the computational social sciences and humanities and proceeds to discuss the technological innovations and design choices behind social media observatories currently under development for the study of opinions related to cultural and societal issues in European spaces. Notable attention is devoted to the construction of Penelope: an open, web-services-based infrastructure that allows different user groups to consult and contribute digital tools and observatories that suit their analytical needs. The potential and the limitations of this approach are discussed on the basis of a climate change opinion observatory that implements text analysis tools to study opinion dynamics concerning themes such as global warming. Throughout, the article explicitly acknowledges and addresses potential risks of the machine-guided and human-incentivized study of opinion dynamics. Concluding remarks are devoted to a synthesis of the ethical and epistemological implications of the exercise of positioning observatories in contemporary information spaces and to an examination of future pathways for the development of social media observatories.

This paper introduces a novel methodology for extracting semantic frames from text corpora. Building on recent advances in computational construction grammar, the method captures expert knowledge of how semantic frames can be expressed in the form of conventionalised form-meaning pairings, called constructions. By combining these constructions in a semantic parsing process, the frame-semantic structure of a sentence is retrieved through the intermediary of its morpho-syntactic structure. The main advantage of this approach is that state-of-the-art results are achieved, without the need for annotated training data. We demonstrate the method in a case study where causation frames are extracted from English newspaper articles, and compare it to a commonly used approach based on Conditional Random Fields (CRFs). The computational construction grammar approach yields a word-level F1 score of 78.5%, outperforming the CRF approach by 4.5 percentage points.

In order to be able to answer a natural language question, a computational system needs three main capabilities. First, the system needs to be able to analyze the question into a structured query, revealing its component parts and how these are combined. Second, it needs to have access to relevant knowledge sources, such as databases, texts or images. Third, it needs to be able to execute the query on these knowledge sources. This paper focuses on the first capability, presenting a novel approach to semantically parsing questions expressed in natural language. The method makes use of a computational construction grammar model for mapping questions onto their executable semantic representations. We demonstrate and evaluate the methodology on the CLEVR visual question answering benchmark task. Our system achieves a 100% accuracy, effectively solving the language understanding part of the benchmark task. Additionally, we demonstrate how this solution can be embedded in a full visual question answering system, in which a question is answered by executing its semantic representation on an image. The main advantages of the approach include (i) its transparent and interpretable properties, (ii) its extensibility, and (iii) the fact that the method does not rely on any annotated training data.