Scroll Top
10 Old Grimsbury Rd, Banbury OX16 3HG, UK

Fake news Classification through Deep Learning Techniques

Task Brief

You are required to write a Detailed Project Proposal for the Dissertation:

word count: 500-700 words

Detailed Project Proposal

1.  Introduction

The Internet is a significant invention, and many people use it. These folks use it for a variety of objectives. These users have access to a variety of social networking channels (Dewey, 2016). Using these internet platforms, any user can create a post or share news (Shu et al., 2017). User details and user’s posts content is not verified by these sites. As a result, a few individuals attempt to distribute bogus news via these channels. Fake news might be used to spread hype against a society, political party, an organization or an individual (Wang, 2017). Human cannot detect all of this bogus news. As a result, there is a need for a technology that can recognize bogus news automatically.

There are numerous online sites where fake/bogus news can be propagated. Social media platform like Twitter and Facebook etc. comes under this. “Machine learning” (ML) and “Deep Learning” (DP) is a subdivision of “Artificial Intelligence” that promotes the advancement of computers which may learn and implement various tasks (Donepudi, 2019). There are several learning algorithms accessible, including supervised, unsupervised, and reinforcement machine learning algorithms (Reis et al., 2019). The data should be trained by using an algorithm then that data called training data. In such training, for variety of tasks, various algorithms can be use and execute. ML and DL techniques are utilized in a various different industry to perform multiple tasks. Many learning algorithms are there which can be used for prediction and to find hidden context. This research work leads to giving solutions via machine learning and deep learning technique for detecting fake news.

2.  Aim/objective of the project

To develop an accurate and effective ML and DL model that can detect and classify fake news articles from the dataset, using a combination of linguistic, semantic, and contextual features.

3.  Hypothesis/Research question

Q1: Why learning techniques are required to detect fake news?

Q2: Which supervised learning algorithm will give the optimized result?

Q3: How classification techniques can be evaluated?

The following above question will be answered at the end of the research work.

4.  The problem/Short description of the idea

This research work involves the development of a learning-based model that can distinguish between real and fake news by analyzing various features of the dataset through the classification technique. The model should be able to accurately classify data as either fake or real, with a high level of precision and recall.

The objective also highlights the importance of using a combination of linguistic, semantic, and contextual features to improve the accuracy of the model. These features could include sentiment analysis, named entity recognition, topic modeling, and other natural language processing techniques.

Overall, the research objective for fake news detection using machine learning is to develop a reliable and effective solution for identifying and combating the spread of fake news, which has become a growing problem in the digital age.Bottom of Form

5.  How you plan to conduct your research?

Stage 1: Literature review related to the research topic.

Stage 2: Finalizing research methodology.

Stage 3: Evaluating dataset for implementation.

Stage 3: Implementing machine and deep learning techniques to obtain the best optimization result.

Stage 4: Analyzing results and comparison with available literature.

6.  Project plan

 References

Donepudi, P.K., 2019. Automation and machine learning in transforming the financial industry. Asian Business Review9(3), pp.129-138.

Dewey, C. (2016). Facebook has repeatedly trended fake news since firing its human editors. The Washington Post, Oct. 12, 2016.

Reis, J. C. S., Correia, A., Murai, F., Veloso A., & Benevenuto, F. (2019). Supervised Learning for Fake News Detection. IEEE Intelligent Systems, 34(2), 76-81.

Shu, K., Sliva, A., Wang, S., Tang, J. and Liu, H., 2017. Fake news detection on social media: A data mining perspective. ACM SIGKDD explorations newsletter19(1), pp.22-36.

Wang, W.Y., 2017. ” liar, liar pants on fire”: A new benchmark dataset for fake news detection. arXiv preprint arXiv:1705.0064

Related Posts

Leave a comment

× WhatsApp Us