Latent Dirichlet Allocation (LDA) Topic Modelling for Library Science Dissertation -- 2
Budget: £100 – £400 GBP
I'm looking to analyze a corpus of four Word documents (consisting of 39, 40, 30 and 30 pages) for my Masters' dissertation in Library and Information Science. I intend for an expert to apply Latent Dirichlet Allocation (LDA) topic modelling to help reveal the hidden thematic structure within these documents.
The study is as follows: Han, X. "Evolution of research topics in LIS between 1996 and 2019: an analysis based on latent Dirichlet allocation topic model." Scientometrics 125, 2561–2595 (2020). https://doi.org/10.1007/s11192-020-03721-0.
Since that study concludes in 2019, I am extending it from the following year. I need to perform the same analysis for the data I have collected, which is organized into four Word documents, one for each year: 2020, 2021, 2022, and 2023.
I will be responsible for writing and completing the dissertation; I don't have the software or computing know-how to run LDA using Gensim in Python. The freelancer needs to use Gensim.
Key responsibilities:
- Preprocessing the dataset, including text cleaning and formatting
- Applying LDA topic modeling algorithm to the dataset
- Interpreting the results and grouping documents by topics
- Allowing for adjustments based on my input and requirements
- Ensuring procedure is well-documented for reference in my academic work
While my project is scholarly, I want the project's findings to be as clear and approachable as possible. An ideal freelancer would be able to communicate frequently and be open to a collaborative approach.
Credit will be given for the freelancer who works on the project. Need a fast turnaround, must be completed within 3 days.
The study is as follows: Han, X. "Evolution of research topics in LIS between 1996 and 2019: an analysis based on latent Dirichlet allocation topic model." Scientometrics 125, 2561–2595 (2020). https://doi.org/10.1007/s11192-020-03721-0.
Since that study concludes in 2019, I am extending it from the following year. I need to perform the same analysis for the data I have collected, which is organized into four Word documents, one for each year: 2020, 2021, 2022, and 2023.
I will be responsible for writing and completing the dissertation; I don't have the software or computing know-how to run LDA using Gensim in Python. The freelancer needs to use Gensim.
Key responsibilities:
- Preprocessing the dataset, including text cleaning and formatting
- Applying LDA topic modeling algorithm to the dataset
- Interpreting the results and grouping documents by topics
- Allowing for adjustments based on my input and requirements
- Ensuring procedure is well-documented for reference in my academic work
While my project is scholarly, I want the project's findings to be as clear and approachable as possible. An ideal freelancer would be able to communicate frequently and be open to a collaborative approach.
Credit will be given for the freelancer who works on the project. Need a fast turnaround, must be completed within 3 days.