Innovation in hyperlink and social media networks: Comparing connection strategies of innovative companies in hyperlink and social media networks.

This paper seeks to unveil how (geospatial) connection strategies associated with business innovation, differ between geolocated social media and hyperlink company networks. Thereby, we provide a first step towards understanding connection strategies of innovative companies on social media platforms. For this purpose, we build a hyperlink and Twitter follower network for 11,892 companies in the information technology (IT) sector and compare them along four dimensions. First, underlying network structures were assessed. Second, we asserted information flow patterns between companies with the help of centrality measures. Third, geographic and cognitive proximities of companies were compared. Fourth, the influence of company characteristics was examined through linear and logistic regression models. This comparison revealed, that on a general level the basic connection patterns of the hyperlink and Twitter network differ. Nevertheless, the geospatial dimension (geographic proximity) and the knowledge base of a company (cognitive proximity) appear to have a similar influence on the decision to connect with other companies on Twitter and via hyperlinks. Further, the results suggest that innovative companies most likely align their connection strategies across hyperlink and Twitter networks. Thus, business innovation might effect connection strategies across online company networks in a comparable manner.

An integrated data framework for policy guidance during the coronavirus pandemic: Towards real-time decision support for economic policymakers.

Usually, official and survey-based statistics guide policymakers in their choice of response instruments to economic crises. However, in an early phase, after a sudden and unforeseen shock has caused unexpected and fast-changing dynamics, data from traditional statistics are only available with non-negligible time delays. This leaves policymakers uncertain about how to most effectively manage their economic countermeasures to support businesses, especially when they need to respond quickly, as in the COVID-19 pandemic. Given this information deficit, we propose a framework that guided policymakers throughout all stages of this unforeseen economic shock by providing timely and reliable sources of firm-level data as a basis to make informed policy decisions. We do so by combining early stage 'ad hoc' web analyses, 'follow-up' business surveys, and 'retrospective' analyses of firm outcomes. A particular focus of our framework is on assessing the early effects of the pandemic, using highly dynamic and large-scale data from corporate websites. Most notably, we show that textual references to the coronavirus pandemic published on a large sample of company websites and state-of-the-art text analysis methods allowed to capture the heterogeneity of the pandemic's effects at a very early stage and entailed a leading indication on later movements in firm credit ratings. While the proposed framework is specific to the COVID-19 pandemic, the integration of results obtained from real-time online sources in the design of subsequent surveys and their value in forecasting firm-level outcomes typically targeted by policy measures, is a first step towards a more timely and holistic approach for policy guidance in times of economic shocks.

Greenwashing in the US metal industry? A novel approach combining SO2 concentrations from satellite data, a plant-level firm database and web text mining.

This study deals with the issue of greenwashing, i.e. the false portrayal of companies as environmentally friendly. The analysis focuses on the US metal industry, which is a major emission source of sulfur dioxide (SO2), one of the most harmful air pollutants. One way to monitor the distribution of atmospheric SO2 concentrations is through satellite data from the Sentinel-5P programme, which represents a major advance due to its unprecedented spatial resolution. In this paper, Sentinel-5P remote sensing data was combined with a plant-level firm database to investigate the relationship between the US metal industry and SO2 concentrations using a spatial regression analysis. Additionally, this study considered web text data, classifying companies based on their websites in order to depict their self-portrayal on the topic of sustainability. In doing so, we investigated the topic of greenwashing, i.e. whether or not a positive self-portrayal regarding sustainability is related to lower local SO2 concentrations. Our results indicated a general, positive correlation between the number of employees in the metal industry and local SO2 concentrations. The web-based analysis showed that only 8% of companies in the metal industry could be classified as engaged in sustainability based on their websites. The regression analyses indicated that these self-reported "sustainable" companies had a weaker effect on local SO2 concentrations compared to their "non-sustainable" counterparts, which we interpreted as an indication of the absence of general greenwashing in the US metal industry. However, the large share of firms without a website and lack of specificity of the text classification model were limitations to our methodology.

Predicting innovative firms using web mining and deep learning.

Evidence-based STI (science, technology, and innovation) policy making requires accurate indicators of innovation in order to promote economic growth. However, traditional indicators from patents and questionnaire-based surveys often lack coverage, granularity as well as timeliness and may involve high data collection costs, especially when conducted at a large scale. Consequently, they struggle to provide policy makers and scientists with the full picture of the current state of the innovation system. In this paper, we propose a first approach on generating web-based innovation indicators which may have the potential to overcome some of the shortcomings of traditional indicators. Specifically, we develop a method to identify product innovator firms at a large scale and very low costs. We use traditional firm-level indicators from a questionnaire-based innovation survey (German Community Innovation Survey) to train an artificial neural network classification model on labelled (product innovator/no product innovator) web texts of surveyed firms. Subsequently, we apply this classification model to the web texts of hundreds of thousands of firms in Germany to predict whether they are product innovators or not. We then compare these predictions to firm-level patent statistics, survey extrapolation benchmark data, and regional innovation indicators. The results show that our approach produces reliable predictions and has the potential to be a valuable and highly cost-efficient addition to the existing set of innovation indicators, especially due to its coverage and regional granularity.