Natural language processing for urban research: A systematic review

Prospective for urban informatics

The specialization of different urban sectors, theories, and technologies and their confluence in city development have led to a greatly accelerated growth in urban informatics, the transdisciplinary field for understanding and developing the city through new information technologies. While this young and highly promising field has attracted multiple reviews of its advances and outlook for its future, it would be instructive to probe further into the research initiatives of this rapidly evolving field, to provide reference to the development of not only urban informatics, but moreover the future of cities as a whole. This article thus presents a collection of research initiatives for urban informatics, based on the reviews of the state of the art in this field. The initiatives cover three levels, namely the future of urban science; core enabling technologies including geospatial artificial intelligence, high-definition mapping, quantum computing, artificial intelligence and the internet of things (AIoT), digital twins, explainable artificial intelligence, distributed machine learning, privacy-preserving deep learning, and applications in urban design and planning, transport, location-based services, and the metaverse, together with a discussion of algorithmic and data-driven approaches. The article concludes with hopes for the future development of urban informatics and focusses on the balance between our ever-increasing reliance on technology and important societal concerns.

Climate Change Sentiment Analysis Using Lexicon, Machine Learning and Hybrid Approaches

The emissions of greenhouse gases, such as carbon dioxide, into the biosphere have the consequence of warming up the planet, hence the existence of climate change. Sentiment analysis has been a popular subject and there has been a plethora of research conducted in this area in recent decades, typically on social media platforms such as Twitter, due to the proliferation of data generated today during discussions on climate change. However, there is not much research on the performances of different sentiment analysis approaches using lexicon, machine learning and hybrid methods, particularly within this domain-specific sentiment. This study aims to find the most effective sentiment analysis approach for climate change tweets and related domains by performing a comparative evaluation of various sentiment analysis approaches. In this context, seven lexicon-based approaches were used, namely SentiWordNet, TextBlob, VADER, SentiStrength, Hu and Liu, MPQA, and WKWSCI. Meanwhile, three machine learning classifiers were used, namely Support Vector Machine, Naïve Bayes, and Logistic Regression, by using two feature extraction techniques, which were Bag-of-Words and TF–IDF. Next, the hybridization between lexicon-based and machine learning-based approaches was performed. The results indicate that the hybrid method outperformed the other two approaches, with hybrid TextBlob and Logistic Regression achieving an F1-score of 75.3%; thus, this has been chosen as the most effective approach. This study also found that lemmatization improved the accuracy of machine learning and hybrid approaches by 1.6%. Meanwhile, the TF–IDF feature extraction technique was slightly better than BoW by increasing the accuracy of the Logistic Regression classifier by 0.6%. However, TF–IDF and BoW had an identical effect on SVM and NB. Future works will include investigating the suitability of deep learning approaches toward this domain-specific sentiment on social media platforms.