No abstract

In the context of Futures Studies, the scenario development process permits to make assumptions on what the futures can be in order to support better today decisions. In the initial stages of the scenario building (Framing and Scanning phases), the process requires much time and efforts to scanning data and information (reading of documents, literature review and consultation of experts) to understand more about the object of the foresight study. The daily use of social networks causes an exponential increase of data and for this reason here we deal with the problem of speeding up and optimizing the Scanning phase by applying a new combined method based on the analysis of tweets with the use of unsupervised classification models, text-mining and spatial data mining techniques. For the purpose of having a qualitative overview, we applied the bag-of-words model and a Sentiment Analysis with the Afinn and Vader algorithms. Then, in order to extrapolate the influence factors, and the relevant key factors (Kayser and Blind, 2017; 2020) the Latent Dirichlet Allocation (LDA) was used (Tong and Zhang, 2016). Furthermore, to acquire also spatial information we used spatial data mining technique to extract georeferenced data from which it was possible to analyse and obtain a geographic analysis of the data. To showcase our method, we provide an example using Covid-19 tweets (Uhl and Schiebel, 2017), upon which 5 topics and 6 key factors have been extracted. In the last instance, for each influence factor, a cartogram was created through the relative frequencies in order to have a spatial distribution of the users discussing each particular topic. The results fully answer the research objectives and the model used could be a new approach that can offer benefits in the scenario developments process.

No abstract

No abstract

The Delphi-based scenarios (DBS) development implies the assumption of different choices, through the gathering of information and the assessment of alternative resolutions (Panpatte and Takale, 2019). During the last decades, the spread of environmental hazards has increased quickly, much to request different responses in order to develop a sustainable future for humanity planning the present (McMichael and Lindgren, 2011). Since the DBS is a creative process (Nowack et al., 2011), different figures are selected to make choices, including academics, stakeholders and citizens. However, one of the main challenges remains the measurement of expertise, in fact, during the process, the experts should be assessed based on their competences in order to avoid any conflict in the final results and, eventually, weigh their answers. In recent years, some contributions adopted the self-assessments for the experts’ evaluation (Sossa et al., 2019), but many issues still remain (such as strong subjectivity and cognitive biases which produce over or underestimation). We develop a new method to estimate the expertise by using Natural Language Processing to acquire information, extracting the contributions of experts in each topic. First, starting from a draft list of selected experts, we identify the category of reference (e.g., academia, industry, local authority, citizens etc.). We build a data repository with the personal pages (URLs) of each expert to then use Python to extract from the URLs, the number of contributions related to a keyword, different for each category (e.g., publications for academics, reports and projects for stakeholders etc.). Finally, we proceed adopting a coefficient of production with a weighted sum of the results. To practically demonstrate our approach, we applied this method to a cohort of known experts, part of the “Smart control of the climate resilience” (SCORE) H2020 European project to estimate their expertise in specific areas.