In an earlier paper, a novel method to pre-process image data for use in Artificial Neural-Network (ANN) classification was presented. This method requires an additional training stage prior to the main learning phase of the ANN. In this extra stage, an additional algorithm (a Selection method) is used to generate the data that is required to construct the final preprocessor. As part of the introduction of that method, it was presented with a single Selection method that was termed Saliency Heat Mapping. This paper will present a number of alternative Selection methods and compare how effective they are against a sample problem.
With many options for text preprocessing techniques, choosing the most efficient methodology is important for both accuracy and computational expense. Online text often contains non-standard English, spelling errors, colloquialisms, emojis, slang and many other variations that affect current natural language processing tools, with no clear guidelines for preprocessing this type of text. In this work we analyse text preprocessing techniques using a data set of online reviews scraped from iTunes and Google Play store. The objective is to measure the efficacy of different combinations of these techniques to maximise the amount of detected sentiment in a dataset of 438,157 reviews. Sentiment detection was performed by two state-ofthe-art sentiment analysers (RoBERTa and VADER). Statistical analysis of the results suggest preprocessing strategies for maximising sentiment detected within mental health app reviews and similar text formats.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.