tkxwaweru/construct_assist

A web application that uses sentiment analysis to recommend construction service providers and professionals in Kenya. # CONSTRUCT-ASSIST ## Quick Links - Introduction - Project installation - Running the project ## Introduction Construct-Assist is a web application that was developed to ease the acquisition of reliable construction professionals and service providers in Kenya. In Kenya, a major problem facing the construction industry is the scarcity of skilled and reliable professionals and service providers within the field. As a result of this, whenever foreign labour is unavailable, unskilled labour is often relied upon resulting in issues such as poor quality construction work and on the extreme end fatalities within the construction sites. Construct-Assist provides project managers with a tools that allows them to review the services of the professionals or service providers that they worked with using English/Swahili or a mix of both languages. The system utilizes a sentiment analysis model in the backend to classify the reviews and thus classify professionals or service providers that are reliable or unreliable. Only those that are classified as reliable shall appear to project managers in recruitment searches. The web application was developed using CodeIgniter4, the model was trained using Jupyter Notebook and the model API was developed using python and was tested locally using Uvicorn. ## Project installation Fork and clone this repository. Run the following command in your terminal to clone the forked repository: ```{code} git clone ``` Copy the link to the GitHub repository. You can specify your own repository name. ### Python dependencies: Open your terminal and create a virtual python environment to store all the required dependencies to run this project. The project was created using python version 3.11.7 which can be installed automatically when working with anaconda environments or can be downloaded directly from here. If you prefer to use python's venv facility: ```{code} python3 -m venv environment_name ``` You can read more on working with py …