Semantic Fusion with Deep Learning and Formal Ontologies for Evaluation of Policies and Initiatives in the Smart City Domain

Round 1

Reviewer 1 Report

This paper presents a knowledge elicitation methodology for the evaluation of smart cities. The motivation and research review with this issue are clear. In addition, technologies utilized for this methodology are also clear from both methodological and technical perspectives.

Only one matter which I wonder about is whether the context analysis presented here could distinguish the explicit and implicit meaning of the terms in the text. I think the authors should include this discussion clearly since the system will relate to the evaluation.

Author Response

Question: Can the context analysis presented here could distinguish the explicit and implicit meaning of the terms in the text. I think the authors should include this discussion clearly since the system will relate to the evaluation.

Answer: Thank you very much for your comment. We agree that implicit knowledge is very important for knowledge discovery in text. The ultimate goal of this research is to abstract implicit knowledge in text into explicit knowledge by using ontology concepts. In our research, we capture implicit knowledge by applying query expansion from two types of sources; knowledge-based and deep learning. For knowledge-based sources we use synonyms and entailments from Wordnet while the deep learning techniques use word similarities in the domain specific index.

We have updated the following text to section 3.2.3 to clarify how we address implicit knowledge and explicit knowledge.

There are some cases where a WordNet term is not mapped into a SUMO concept. In such cases we perform query expansion for the term to identify synonyms and entailments of the word provided in the original text. Research show that query expansion improves knowledge discovery in text [Boer 2016].  We perform query expansion using both knowledge-based and deep learning methods. For the knowledge-based methods, we use the synonym and entailment facilities of Wordnet while for the deep leaning methods we word similarity in the domain-specific Word2Vec high-dimensional space. Each expanded term added to the concept map will have a relevance probability proportional with its degree of similarity to the original word. We further evaluate the relevance of each expanded term using a Couquet Integral method to identify the terms that are relevant in both general and domain specific indexes.  For more information on query expansion, the reader is directed to read [ Ergin Barb 2020].   Finally, we map the expanded term set into the SUMO ontology.

Reviewer 2 Report

Dear Authors

the smart city isn't based on new technological inventions. Today main problem for smart cities is global warming and natural hazards. For cities are the problem with the supply of drinking water for inhibitions, the flash rain, the hurricane, the high temperature,  the deep freeze, and earthquakes. On figures and tables, I don't see a discussion about it, it is only in one table 6 that is in short words. I propose to extend this subject on figures 5-8 and text which describes those images.  Present seeking for smart cities must have analyzed the problem of natural hazards.  Look for example Harappa and Mohendgo Daro, both of those cities collapsed due to climate changes.

Another problem is the supply of fresh vegetables and meat for inhabitants. If we like to reduce the costs of food in shops, we must reduce the distance between markets and harvest fields. 

Author Response

Question: On figures and tables, I don't see a discussion about supply of drinking water for inhibitions, the flash rain, the hurricane, the high temperature, the deep freeze, and earthquakes, it is only in one table 6 that is in short words. I propose to extend this subject on figures 5-8 and text which describes those images. Present seeking for smart cities must have analyzed the problem of natural hazards.

Answer: Thank you very much for your comment. We agree that climate change issues are important and should be addressed in smart city policies. The goal of our research is to show decision makers gaps and weaknesses in their policies. As seen in Table 6, the three documents that we analyzed address the topic of climate change and sustainability differently. These topics are discussed in UN and USA policies while the Philadelphia policy does not address the issue. This clearly shows a policy gap that can be further discussed among local Philadelphia policy makers.

We have added the following paragraph to section 4.2 to reflect the suggestion from the reviewer.

On these figures we can also observe a different approach to categories that relate to processes, geography, and society. The importance of these categories increases with an increase in the locality of the policy. At the most global level, the UN policy only talks about these issues in general terms without too much emphasis. We attribute this to the fact that these issues need to be addressed at a local level. The USA policy emphasizes more on these categories by stressing the role of related categories such as Government and Engineering. At the most local level, the Philadelphia policy has the strongest focus on these policies and adds information on specific topics that are used in the implementation of these policies such as technology, media and transportation. It is also important to mention that, as it will be shown later in this section, the subtopics addressed at each level vary with the locality degree. For example, climate change, which is typically included in these categories, is addressed differently by the three policies.

We have also updated the future work section to reflect the suggestion from the reviewer.

Our future work will scale up the number of policy documents analyzed where the benefit of automatic knowledge extraction will be apparent to decision makers and analysts. We will also evaluate the relevance of these policies to areas of interest for communities such as climate change, impact of natural hazards, and supply. Furthermore, we will extend this work and focus on in-depth evaluation of smart city policy development procedures using mereotopology principles. We will evaluate the smart city information topology at different mereological levels to identify gaps or overlaps in policies. The knowledge gained from this process can be used to address policy areas that need more focus for a consistent allocation of financial and human effort.