Constructing and understanding arguments is often difficult but key to both philosophyand other parts of the everyday life. Some methods to ease this task has been developed.One of the methods developed within informal reasoning is argument diagramming, amethod to structure and visualize arguments. This essay takes a complicated argumentabout the fate of the universe, put forward by futurist Ray Kurzweil in his book TheSingularity is Near, as well as some critique published against said argument, as a casestudy for the application of argument diagramming on unstructured arguments fromoutside the field of philosophy. To arrive at a diagram that can be easily grasped andread but still contains all information of the original argument, this essay developsa method of splitting sub-diagrams off of a main diagram. Analysing the resultingdiagrams shows that the plausibility of Kurzweil’s argument is heavily dependent on afew, critical premises at the lower levels of the diagram.

With our modern deluge of information through social media, news and blogs, the importance of giving our children a better understanding of source criticism and critical thinking has become increasingly clear. In the field of critical thinking, the use of argument mapping software, a visual way of structuring arguments, has been shown to increase the understanding of arguments, and college students using the method score as much as three times higher on critical thinking tests.  This thesis presents a simplified digital argument mapping tool, developed in order to explore the feasibility of argument mapping for students in secondary school (aged 13-15). The tool is then tested on two secondary school classes. The thesis shows that the students are proficient at basic argument mapping with the tool, but also that the more complex facets of the method require more instruction in order to be used by the students. Recommendations are presented for further development of the argument mapping tool, as well as further studies of critical thinking using argument mapping in secondary school. The thesis has shown the argument mapping has potential for use in secondary school, and should be further studied. / Med vårt moderna överflöd av information genom sociala media, nyheter och bloggar, så ökar vikten av att ge våra unga en bättre förståelse för källkritik och kritiskt tänkande. I fältet kritiskt tänkande har en metod som kallas argument mapping, en visuell metod för att strukturera argument, visats öka förståelsen av argument, samt vid användning studenter i universitet har metoden ökat resultaten på test i kritiskt tänkande upp till tre gånger. Uppsatsen presenterar ett förenklat digitalt argument mapping-verktyg, utvecklat för att studera hur elever på högstadiet (13-15 år) kan använda sig av metoden, som sedan testas på två högstadieklasser. Resultatet visar att studenterna klarar av grundläggande argument mapping med verktyget, men att de mer komplexa delarna av metoden behöver vidare instruktion för att eleverna ska kunna förstå. Rekommendationer presenteras baserat på den data som samlats in, både för vidareutveckling av det designade verktyget, samt för framtida studier av kritiskt tänkande och argument mapping i högstadiet. Uppsatsen visar att argument mapping har potential för användning av högstadieelever, och bör därmed undersökas vidare.

The growing volume of opinion data presents a significant challenge for policymakers striving to distill public sentiment into actionable decisions. This study aims to explore the capability of large language models (LLMs) to synthesize public opinion data into coherent policy recommendations. We specifically leverage Mistral 7B and Mixtral 8x7B models for text generation and have developed an architecture to process vast amounts of unstructured information, integrate diverse viewpoints, and extract actionable insights aligned with public opinion. Using a retrospective data analysis of the Polis platform debates published by the Computational Democracy Project, this study examines multiple datasets that span local and national issues with 1600 statements posted and voted upon by over 3400 participants. Through content moderation, topic modeling, semantic structure extraction, insight generation, and argument mapping, we dissect and interpret the comments, leveraging voting data and LLMs for both quantitative and qualitative insights. A key contribution of this thesis is demonstrating how LLM reasoning techniques can enhance content moderation. Our content moderation approach shows performance improvements using comment deconstruction in multi-class classification, underscoring the trade-offs between moderation strategies and emphasizing a balance between precision and cautious moderation. Using comment clustering, we establish a hierarchy of semantically linked topics, facilitating an understanding of thematic structures and the generation of actionable insights. The generated argument maps visually represent the relationships between topics and insights, and highlight popular opinions. Future work will leverage advanced semantic extraction and reasoning techniques to enhance insight generation further. We also plan to generalize our techniques to other major discussion platforms, including Kialo. Our work contributes to the understanding of using LLMs for policymaking and offers a novel approach to structuring complex debates and translating public opinion into actionable policy insights.