P2P Lending Sentiment Analysis in Indonesian Online News

DOI

10.2991/aisr.k.200424.006How to use a DOI?

Keywords

fintech, P2P Lending, sentiment analysis, classification

Abstract

Fintech has improved from a few years ago and has put regulators under pressure to find a legal framework that allows fintech to operate in the formal financial sector and provide appropriate protection for customers. At present, many online news in Indonesia contain articles about Fintech, especially P2P (Peer to peer) Lending. The positive and negative sides of the development of P2P Lending are interesting for further investigation. This study aims to determine the best text classification techniques from P2P Lending sentiment analysis on Indonesian Online News. This research compared four algorithms which are Multinomial Naïve Bayes (NB), Logistic Regression (LR), Support Vector Machine (SVM) and Random Forest (RF). The experiment was carried out using features combination and the model was measured using 10-fold cross validation. The result is the SVM classification model achieves the highest accuracy score of 63.61% on the TFIDF Unigram-Trigram feature.

Copyright

© 2020, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Ryan Randy SURYONO
AU  - Indra BUDI
PY  - 2020
DA  - 2020/05/06
TI  - P2P Lending Sentiment Analysis in Indonesian Online News
BT  - Proceedings of the Sriwijaya International Conference on Information Technology and Its Applications (SICONIAN 2019)
PB  - Atlantis Press
SP  - 39
EP  - 44
SN  - 1951-6851
UR  - https://doi.org/10.2991/aisr.k.200424.006
DO  - 10.2991/aisr.k.200424.006
ID  - SURYONO2020
ER  -