Zbornik radova Fakulteta tehničkih nauka u Novom Sadu

Elektrotehničko i računarsko inženjerstvo

God. 38 Br. 03 (2023): Zbornik radova Fakulteta tehničkih nauka

PREDIKCIJA OCENE APLIKACIJE NA OSNOVU KOMENTARA

  • Marko Mijatović
DOI:
https://doi.org/10.24867/22BE04Mijatovic
Predato
October 20, 2022
Objavljeno
2023-03-04

Apstrakt

U ovom radu predstavljena je specifikacija, implementacija i evaluacija sistema za predikciju ocene na osnovu tekstualnog komentara. Upoređena su dva pristupa – rekurentne neuronske mreže i modeli ansambla.

Reference

[1] D. Monett and H. Stolte, “Predicting Star Ratings based on Annotated Reviews of Mobile Apps,” Oct. 2016, pp. 421–428. doi: 10.15439/2016F141.
[2] M. Umer, I. Ashraf, A. Mehmood, S. Ullah, and G. S. Choi, “Predicting numeric ratings for Google apps using text features and ensemble learning,” ETRI Journal, vol. 43, no. 1, pp. 95–108, Feb. 2021, doi: 10.4218/etrij.2019-0443.
[3] B. Gezici, N. Bolucu, A. Tarhan, and B. Can, “Neural Sentiment Analysis of User Reviews to Predict User Ratings,” in 2019 4th International Conference on Computer Science and Engineering (UBMK), Samsun, Turkey, Sep. 2019, pp. 629–634. doi: 10.1109/UBMK.2019.8907234.
[4] https://www.kaggle.com/datasets/prakharrathi25/google-play-store-reviews