Fake Product Review Detection
As we know that the mobile application market is rising day by day. Many users use mobile applications for various purposes. On Google play store mobile applications have grown to 3.5 million. There is also an increase in the number of fraud applications. As fake reviews pose a general and damaging
2025-06-28 16:27:13 - Adil Khan
Fake Product Review Detection
Project Area of Specialization Artificial IntelligenceProject SummaryAs we know that the mobile application market is rising day by day. Many users use mobile applications for various purposes. On Google play store mobile applications have grown to 3.5 million. There is also an increase in the number of fraud applications. As fake reviews pose a general and damaging problem, helping consumers and businesses differentiate ingenuous reviews from fake ones remains a vital but challenging task. Fake review detection can combine manual efforts, supervised ML, and heuristic methods (Fontanarava et al., 2017). Some approaches in the literature focus solely on features extracted from the review text. Linguistic characteristics range from counting the frequency of words or n-grams (Viviani and Pasi, 2017) to more advanced approaches relying on distributional semantics (Lee et al., 2016). However, despite the progress made in detection studies, considerable challenges lie ahead
Project Objectives- To give better adaptability and well-disposed Graphical UI to have the best insight
- To foster a framework that tracks down positioning, rating, and audit comportment for testing thoughts and club based improvement to consolidate all the underwriting for the discovery of misrepresentation
- Composing incorporates contemplates that perform an examination on a social event of utilizations mined from an application store.
- The essential target is to foster a framework that tracks down positioning, rating, and survey practices for analyzing ideas and afterward conglomeration dependent on advancement to consolidate every one of the suggestions for the location of extortion.
- This task addresses the new original methodology for the improvement of a positioning misrepresentation identification framework for portable applications. At first, the ID of rating based idea is finished
Initially, identification of rating based suggestion is done. Then identification of review based suggestion then by leading mining sessions ranking fraud suggestion is collected. And finally, the system performs the aggregation of all three suggestions to detect fraud apps. This method will offer considerable benefits and provides an opportunity to prevent fraudulent apps in the market.
Benefits of the ProjectAs fake reviews pose a general and damaging problem, helping consumers and businesses differentiate ingenuous reviews from fake ones remains a vital but challenging task (Crawford et al., 2015). Fake review detection can combine manual efforts, supervised ML, and heuristic methods (Fontanarava et al., 2017). Some approaches in the literature focus solely on features extracted from the review text. Linguistic characteristics range from counting the frequency of words or n-grams (Viviani and Pasi, 2017) to more advanced approaches relying on distributional semantics (Lee et al., 2016). However, despite the progress made in detection studies, considerable challenges lie ahead
Technical Details of Final Deliverable- System necessities, and for the web app, minimum accommodating requirements as well
- Sentimental analysis
- Necessary information regarding the sentimental analysis
- Setup information and diagnosing documents
| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 68000 | |||
| GeForce GTX 1070 | Equipment | 1 | 68000 | 68000 |