The Effects of Natural Language Processing on Big Data Analysis: Sentiment Analysis Case Study

Khader, Mariam; Awajan, Arafat; Al‐Naymat, Ghazi

doi:10.1109/acit.2018.8672697

Cited by 27 publications

(18 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Chi-square method used for feature selection helps to reduce the dimensionality as well as noise in data and increase the accuracy of classifier from 81.5 to 92.3 in TF-IDF, 83 to 90 in FF and 83.1 to 93 in FP [21]. Number of feature selected highly effect the accuracy of result but after a limit increase in size of feature set does not increase classification accuracy [22]- [25].…”

Section: E Feature Selection Methods and Number Of Features Selectedmentioning

confidence: 99%

“…Classification accuracy highly depends on data quality and various researches [18]- [21] show the effect of preprocessing technique on efficiency of classification. Effects of feature selection methods and number of features on classification accuracy are explored in various researches [22]- [28]. All these factors collectively effect overall efficiency and need to be addressed in sentiment analysis.…”

Section: Literature Surveymentioning

confidence: 99%

See 1 more Smart Citation

Review of Factors Affecting Efficiency of Twitter Data Sentiment Analysis

Sangeeta¹,

Gill²

2020

IJCTE

View full text Add to dashboard Cite

Twitter sentiment analysis has been explored in various domains including Business reviews, Political forecasting, decision support, Movie reviews and many more. The nature of data collected by Twitter imposes several challenges for sentiment analysis. There are other factors also like the selected classifier, multiclass sentiment analysis, feature selection method, number of feature selected, level of preprocessing, preprocessing techniques involved that can affect the accuracy of classification. This paper discusses various factors affecting the accuracy of Twitter sentiment analysis. Consideration of these factors can be very beneficial while designing an efficient classification model for twitter sentiment analysis. The survey also focuses on various metrics used for representation of sentiment analysis result and their relevance.

show abstract

Section: E Feature Selection Methods and Number Of Features Selectedmentioning

confidence: 99%

Section: Literature Surveymentioning

confidence: 99%

Review of Factors Affecting Efficiency of Twitter Data Sentiment Analysis

Sangeeta¹,

Gill²

2020

IJCTE

View full text Add to dashboard Cite

show abstract

“…The stopword list which is used is made by itself, refers to the context of words which are often used in hospital services and numbers. Number have no effect on sentiment analysis, and removing them can reduce noise and increase efficiency [27]. An example of a stopword list used is shown in Table 4.…”

Section: Conversation Analysismentioning

confidence: 99%

Sentiments analysis of customer satisfaction in public services using K-nearest neighbors algorithm and natural language processing approach

2021

View full text Add to dashboard Cite

Customer satisfaction is very important for public service providers, customer satisfaction can be delivered with a survey application or writing criticism that can be used to evaluate and improve service. Unfortunately, there are only a few customers who are willing to give an assessment. The survey application cannot represent the overall feeling of the customer, so it is necessary to analyze the content of the conversation between the customer and the service personnel to determine the level of customer satisfaction. In small amounts, it can be done manually, but in large quantities it is more effective to use the system. A solution is needed in the form of a system that converts voice conversations into text and analyzes customer satisfaction to obtain information for evaluation and improvement of services. This research uses Knearest neighbors (KNN) and term frequency-inverse document frequency (TF-IDF) algorithm with natural language processing (NLP) approach to classify conversations into 2 classes, "satisfied" and " dissatisfied ". The results of this study received 74.00% accuracy, 76.00% precision and 73.08% recall. In conversations with the label "satisfied" shows customers satisfied with the service and fulfillment of customer desires, while in conversations with the label "not satisfied" customers are less satisfied with the waiting time.

show abstract

“…Daftar stopword yang digunakan dibuat sendiri mengacu pada konteks kata yang sering dipakai dalam Dapat dilihat pada Tabel 4, kata "yang" merupakan salah satu daftar stopword yang paling banyak muncul, yaitu sebanyak 214 kali, dan kata "di" yang muncul sebanyak 104 kali. Selain dalam bentuk kata angka juga masuk ke dalam stopword, angka tidak berpengaruh pada analisis sentimen dan dapat dihapus, sehingga dapat mengurangi kebisingan dan meningkatkan efisiensi [26]. Hasil keseluruhan proses prapemrosesan dapat dilihat pada Tabel 5.…”

Section: Analisis Ulasanunclassified

Analisis Sentimen pada Ulasan Pembelian Produk di Marketplace Shopee Menggunakan Pendekatan Natural Language Processing

Muktafin¹,

Kusrini²,

Luthfi³

2020

eksplora

View full text Add to dashboard Cite

Ulasan produk di marketplace merupakan informasi yang berharga apabila diolah dengan baik. Penjual dapat melakukan analisis ulasan produk untuk mendapat informasi yang dapat digunakan dalam evaluasi produk dan layanan. Kegiatan analisis ulasan produk tidak cukup dengan melihat jumlah bintang, diperlukan melihat seluruh isi komentar ulasan untuk dapat mengetahui maksud dari ulasan. Apabila dalam jumlah sedikit dapat dilakukan secara manual, namun dalam jumlah banyak lebih efektif menggunakan sistem. Dibutuhkan sistem yang mampu menganalisis banyak ulasan dengan efektif agar memudahkan dalam memahami maksud ulasan. Penelitian ini menggunakan algoritma KNN dan TF-IDF dengan pendekatan NLP untuk mengklasifikasikan ulasan produk “hijab instan” ke dalam 2 kelas (positif dan negatif). Klasifikasi menggunakan pendekatan NLP mendapat akurasi sebesar 76,92%, presisi 80,00% dan recall 74,07%, sedangkan tanpa NLP hanya mendapat akurasi sebesar 69,23%, presisi 80,00% dan recall 64,52%. Kata yang sering muncul pada ulasan dapat menggambarkan penilaian pembeli secara umum pada produk. Pada ulasan positif menunjukkan pembeli puas terhadap kualitas, kecepatan pengiriman dan harga barang, sedangkan pada ulasan negatif pembeli kecewa pada warna, dan jumlah barang yang dikirim tidak sama dengan yang dipesan.

show abstract

The Effects of Natural Language Processing on Big Data Analysis: Sentiment Analysis Case Study

Cited by 27 publications

References 11 publications

Review of Factors Affecting Efficiency of Twitter Data Sentiment Analysis

Review of Factors Affecting Efficiency of Twitter Data Sentiment Analysis

Sentiments analysis of customer satisfaction in public services using K-nearest neighbors algorithm and natural language processing approach

Analisis Sentimen pada Ulasan Pembelian Produk di Marketplace Shopee Menggunakan Pendekatan Natural Language Processing

Contact Info

Product

Resources

About