According to the discussion between my supervisor and me, we agree that my initial thought of comparing the performance of existing fraud detection tools on electronic product reviews is hard to work on well as we cannot find golden standard corpus in the domain of electronic product that is already been labelled as fake review or reliable review. At that point, I found a corpus on Kaggle and my supervisor liked it, so he provide me with another preliminary topic ‘A comparison study of sentiment analysis tools in the context of user reviews based on explicit rating measures’ based on that mobile phone corpus (https://www.kaggle.com/PromptCloudHQ/amazon-reviews-unlocked-mobile-phones). He wanted me to look into reviewing sentiment analysis tools based on the Kaggle corpus or similar. Your gold standard is the rating, so a review with 4-5 stars is positive, 3 is neutral and 1-2 is negative. Then you could test the performance of the tools against the rating to see whether the detection of the sentiment agrees with the rating. So last meeting he asked me to find out the 2-3 existing sentiment analysis tools (he also provide me with a tool named GATE https://gate.ac.uk/) that I want to investigate, and find one or two more corpus with rating and reviews similar with the mobile phone corpus (He suggested the restaurant reviews with star rating). Therefore, I can compare them two by two (two tools and two corpus) and see their performance and discuss according to the result. Also in the last email, he said if I cannot find the corpus with rating, I can also use the labelled corpus (e.g. https://nlp.stanford.edu/sentiment/code.html).
But I am still confused about what is the aim of this type of comparative research and what question I want to answer in this dissertation topic. So, I want you to help to adjust this topic to be more meaningful and feasible. But if you think that this topic makes little sense, the research domain of my supervisor is NLP and particularly negation detection (He published an article about Negation detection on archeology and one of his suggested dissertation area for us is Negation Detection approaches in the humanities domain), could you please find a feasible topic in this area.
At the same time, I also have a concern that these sentiment analysis tools are designed with multi-domain issues in mind (it can also be said that the tools are not domain-specific), so if I just take the corpus of electronic products and restaurants into account and conduct experiments to test their accuracy, what if the final results are similar and there are no useful discoveries?
[Button id=”1″]
Quality and affordable writing services. Our papers are written to meet your needs, in a personalized manner. You can order essays, annotated bibliography, discussion, research papers, reaction paper, article critique, coursework, projects, case study, term papers, movie review, research proposal, capstone project, speech/presentation, book report/review, and more.
Need Help? Click On The Order Now Button For Help
What Students Are Saying About Us
.......... Customer ID: 12*** | Rating: ⭐⭐⭐⭐⭐"Honestly, I was afraid to send my paper to you, but splendidwritings.com proved they are a trustworthy service. My essay was done in less than a day, and I received a brilliant piece. I didn’t even believe it was my essay at first 🙂 Great job, thank you!"
.......... Customer ID: 14***| Rating: ⭐⭐⭐⭐⭐
"The company has some nice prices and good content. I ordered a term paper here and got a very good one. I'll keep ordering from this website."
