Search

This study aims to analyse solar power acceptance by different methods in various knowledge domains to gain a holistic view of global, regional, and local acceptance. This includes considering different related aspects of solar energy, including the overall concept, solar panel, the device converting sunlight into electricity, and photovoltaics, the technology. This multidisciplinary approach is possible through the advancement of artificial intelligence technology. Technology acceptance and sentiment, the emotion, are different concepts with slightly different influences on technology deployment. Acceptance can be granted as a social license and can be affected by how the media discusses the technologies. The acceptance further influences investment decisions and wider technology adoption. Sentiment can be obtained by machine or human-made analysis, in which the polarity (positive, negative, or neutral) is defined while the acceptance levels are indicative. This study applies opinion mining, chat generative pre-trained transformer, and generalised aggregated lexical tables methods to analyse the acceptance and sentiment of solar power at different levels. The findings and the original contribution involve highlighting the potential of artificial intelligence to study general acceptance. Artificial intelligence appears capable of providing a fast indication of both media sentiment and the level of acceptance of solar power. Traditional opinion mining seems to be more capable of acknowledging trends. This supports understanding the market environment and factors affecting technology development and deployment. Decision-making can benefit from a fast indication. [Display omitted] • Assessing global, regional, and local acceptance of solar power. • Combining opinion mining, ChatGPT, and CA-GALT to analyse general acceptance. • AI provides a fast indication of both media sentiment and the level of acceptance. • Understanding energy technology acceptance-related chains of reasonings. • Techno-economic context to complement views with causal acceptance models. [ABSTRACT FROM AUTHOR]

Abstract The nature of media image, through either traditional or social media, may have an influence on public acceptance of energy technologies. The potential impact on decision-making can make media image a factor for technology market deployment, similar to technical, legal, and economic factors. Public acceptance tends to be shaped by how technologies are presented in the media. This study compares and analyses the media image of various power production technologies. Editorial and social media are analysed by using the M-Adaptive tool for media monitoring to obtain the media sentiment. The analysis is rather broad, including three million social media platforms and various news outlets in many regions and covering an enormous number of data points, from which this study has selected over 250,000 for further analysis with the help of artificial intelligence. The results indicate that public sentiment towards power production technologies varies among different technologies, and between editorial publications and social media. Editorial content is usually constructed by using news frames, whereas social media includes more emotional content from single users. A potential chain from media image to energy technology market deployment is suggested. The findings support the notion of social media having an increasing role in shaping public opinion, which may need to be acknowledged to a larger extent. Highlights • This paper studies the energy technology media image effect to commercialisation. • This is studied in the case of power technologies. • The method used is opinion mining based on artificial learning machine based media-analysis. [ABSTRACT FROM AUTHOR]

This paper analyses the media image of solar power in order to understand the recent technology development trends. The increase in both solar PV panels as well as concentrated solar power plants has been influenced by decrease in solar power price, as well as subsidies and general public acceptance. This paper focuses to the latter, through quantitative media analysis. This paper utilises a modern method for media sentiment analysis from both editorial and social media, learning machine based analysis including over 50 000 data points. The results indicate that sentiment toward solar power, especially in social media, has been mostly neutral or positive thus with expected positive effect on technology market deployment. [ABSTRACT FROM AUTHOR]