Sentiment Classification for Film Reviews by Reducing Additional Introduced Sentiment Bias

FERY ARDIANSYAH EFFENDI

Informasi Dasar

99 kali
21.04.3909
006.35
Karya Ilmiah - Skripsi (S1) - Reference

Individual reviews are crucial aspects of the film business as it grows more prominent, with mixed reviews help film sales exponentially. IMDb is a credible source of film reviews posted through a public medium. The problem arises with IMDb site reviews being unstructured and bias-heavy that bias processing classification methods are required to determine the site review’s polarity. This paper evaluates sentiment classification methods by reducing additional introduced sentiment bias to create a balanced classification with a lower polarity bias. Elimination of additional sentiment bias would improve the accuracy in determining the review sentiment. This research limits the dataset by 50.000 rows of randomly extracted reviews from the IMDb website using dataset preparation methods such as Preprocessing, POS-Tagging, and Word Embeddings. Then preprocessed data is used in classification methods such as Artificial Neural Network, and SentiWordNet, SO-Cal. This paper also used bias processing methods such as Hyperparameter Tuning and Additional Introduced Bias Processing Method in SentiWordNet, with outputs evaluated using Accuracy and Polarity Bias Rate metrics. This research yields 77.39 % for ANN, 66.32% for BPM, 75.6% for SO-Cal, and 76.26% for Hybrid classification. Best PBR resulted in two lexicon-based methods on 0.0009 for BPM, and 0.00006 for SO-Cal.

Subjek

Natural language processing
 

Katalog

Sentiment Classification for Film Reviews by Reducing Additional Introduced Sentiment Bias
 
 
Inggris

Sirkulasi

Rp. 0
Rp. 0
Tidak

Pengarang

FERY ARDIANSYAH EFFENDI
Perorangan
Yuliant Sibaroni, Erwin Budi Setiawan
 

Penerbit

Universitas Telkom, S1 Informatika (International Class)
Bandung
2021

Koleksi

Kompetensi

 

Download / Flippingbook

 

Ulasan

Belum ada ulasan yang diberikan
anda harus sign-in untuk memberikan ulasan ke katalog ini