• Piyush Rai
• Dr. Shobhit Sinha

Everyday language, including slang, can be tricky for computers to understand. This is especially true when it comes to automatically figuring out how words can be used in different ways. While researchers have looked at slang through the lens of building dictionaries, understanding emotions, how new slang words are formed, and even interpreting their meaning, there hasn't been much focus on simply finding and identifying slang in the first place. In our study, we explored using powerful computer learning techniques called deep learning to automatically detect and pinpoint slang within sentences. We combined different deep learning models to achieve this, and tested them using a wide range of language features to see how well they could identify slang at the sentence level (is there slang here?) and word level (which exact word is slang?). Interestingly, we found that a key feature of slang is when words are used in unexpected ways, like a verb suddenly becoming a noun (think "going viral"). Our best models achieved an accuracy score of 95% for detecting entire sentences containing slang, and 77% accuracy for pinpointing the exact slang word within a sentence

"Unveiling the Influence of Slang: Machine Learning Insights into Social Media Behavior", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 12, page no.a640-a646, December-2025, Available :http://www.jetir.org/papers/JETIR2512085.pdf

"Unveiling the Influence of Slang: Machine Learning Insights into Social Media Behavior", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 12, page no. ppa640-a646, December-2025, Available at : http://www.jetir.org/papers/JETIR2512085.pdf