Uncover the hidden insights in climate change-related text data to better understand the impact and take informed actions.
Climate Change is a prevailing topic in today's world, everyone is concerned about it and don't know what information to trust as the internet has now become a vast place where anyone can share their own opinion would take it as gospel truth. For this reason, the team decided to create EcoRead, a place where users can search information about climate change.
The increasing urgency of climate change and its potential consequences have motivated us to undertake this project. We believe that by analyzing text data related to climate change, we can gain valuable insights that can help address the issue more effectively.
The project greatly contributes to environmental sustanability in the following ways:
- Accessible Information: Climate change is a critical global issue, and understanding its complexities is essential for informed decision-making and action. By providing summarized and sentiment-analysed content, this tool enables users to quickly grasp the key points and sentiment of climate change-related texts. This promotes awareness and empowers individuals to engage in environmentally sustainable practices and advocacy.
- Efficient Information Consumption: The tool's summarization feature allows users to efficiently consume relevant information without spending excessive time reading lengthy articles. This efficiency can be particularly valuable during time-sensitive events like climate-related emergencies or policy updates, enabling users to stay informed and take appropriate actions promptly.
Our project aims to analyze large volumes of text data related to climate change, such as scientific papers, news articles, social media posts, and policy documents. By using natural language processing techniques, we extract key information, identify trends, and uncover patterns in the data. This analysis can provide valuable insights into the causes, effects, and potential solutions to climate change.
Users can interact with our project by inputting their own text data or accessing pre-analyzed datasets. The system will then perform various analyses, such as sentiment analysis, summaisation, topic modeling, and entity recognition, to extract meaningful information. The benefits of this project include better understanding of climate change and the ability to make informed decisions and take appropriate actions.
To build this project, we used a combination of programming languages and tools. We utilized Python for data preprocessing, natural language processing, and machine learning algorithms. Libraries such as NLTK, pandas, and plotly were used for text analysis tasks. We also employed web scraping techniques to gather data from various sources. The project also utilises Streamlit, an open-source Python library to create the UI for the project.
We were heavily inspired by the revised version of Double Diamond design process, which not only includes visual design, but a full-fledged research cycle in which you must discover and define your problem before tackling your solution & then finally deploy it.
- Discover: a deep dive into the problem we are trying to solve.
- Define: synthesizing the information from the discovery phase into a problem definition.
- Develop: think up solutions to the problem.
- Deliver: pick the best solution and build that.
The following images are how the app looks like:
The team developed both personal and professional growth:
- Technical Skills: We developed and enhanced our expertise and obtained new skills ranging from ML/AI and
- Research Skills: The team had to research a lot on the topic as well as learn new Python libraries that were used for this project.
Developing the application was complex as the was a one person team. I had to do all the research and coding as well as the documentation on my on. While it was a great experience because I got to learn so much, I ended up sacrificing my sleep to finish the application and have a working prototype.
By providing users to summarise articles, upload their own files as well as provide them with a visual representation of how climate change affects people's emotions online, users can make informed-decisions with regards to climate change.
- Sentiment Analysis & Complexity: provide an analysis of the sentiment of text as well as the complexity of text provided.
- Graph Visualisation: visual representation of sentiment analysis.
- Text Summarisation: users can summarise text from articles for quicker information absorption.
Continue developing the application because I want to implement this in our lives! The other thing is to implement the featrures not implemented and work more on the summariser for better results as well as allow users to create their own charts from data that they insert.