Hello everyone, I’m currently working on my masters thesis in which I want to find current and future application patterns of a technology in an industry based on previous researchers done regarding the topic by analyzing the tittle, abstract, conclusion and implications of these article if it is even possible but I’m not sure which data mining method and algorithm should I use to get the best possible results. It would be great if you could give me advices and feedbacks.
Best regards.
Hello there! Not sure if you have keywords available but I would recommend looking into those as well for identifying topics, as they ofter ARE the topics the authors are classifying their work as. You could then identify on which keywords/topics that technology is being used and which keywords that are associated to those first keywords aren't using that technology, which could possibly apply that technology in the future.
For text analysis I would recommend using word embeddings like word2vec and GloVe, or transformers like BERT; there are studies that have already defined academic text corpus that you could check out. You could then measure the similarity between publications that apply and do not apply that technology, in order to calculate the probability of that technology being used in a particular topic.
Hope this helps and good luck with your thesis!
Carlos Emilio Orellana Fantoni thank you so much for helping me out I so as you mentioned I’ve already determined my keywords to collect the articles from Web Of Science and Scopus and apply the method. I’ll look into the softwares you recommended.
Maybe you can try bibliometric analysis, I think it is a suitable way to solve your problem to some extent. CiteSpace or VOSviewer are commonly used in the method.
Choosing the right data mining method and algorithm depends on your use case. There are many different data mining methods and algorithms available, each with its own strengths and weaknesses. Some of the most popular data mining methods include clustering, classification, regression, and association rule mining. To determine which method is best for your use case, you should consider factors such as the size of your dataset, the type of data you are working with, and the specific problem you are trying to solve.
- Badges
- Science topic
- Similar topics
- Methodology
- Research Methodology
- Research Papers