Summary of Effects Of Soft-domain Transfer and Named Entity Information on Deception Detection, by Steven Triplett et al.
Effects of Soft-Domain Transfer and Named Entity Information on Deception Detection
by Steven Triplett, Simon Minami, Rakesh Verma
First submitted to arxiv on: 18 Oct 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes a method for detecting online deception by combining datasets from various domains using transfer learning with fine-tuned BERT models. The authors evaluate the impact of eight different datasets on classifier performance, finding improvements over the baseline. They also investigate the effect of Jensen-Shannon distance between datasets and named entity recognition methods on BERT’s accuracy. The results show notable improvement in accuracy of up to 11.2% when using these techniques. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper tries to solve a big problem: how to know if something written online is true or not. There are many reasons people might lie online, and it’s hard to figure out without actually talking to them. The researchers tested different ways to combine data from various places online, like social media and news sites, to see if they could get better at detecting lies. They found that combining this data with a special kind of AI model called BERT made things better. They also looked at how far apart different datasets were and saw some connections. Finally, they tried adding extra information from named entities in the text and got even more accurate results. |
Keywords
» Artificial intelligence » Bert » Named entity recognition » Transfer learning
