Sentiment analysis based on Support Vector Machine and Big Data

Povoda, Lukáš; Bürget, Radim; Dutta, Malay Kishore

doi:10.1109/tsp.2016.7760939

Cited by 23 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Data diambil dari facebook menggunakan tool scrapping arifScrapper yang dibuat mandiri oleh peneliti dan Stemming merupakan salah satu tahapan dalam proses text pre-processing. Stemming bertujuan untuk mentransofrmasikan kata menjadi kata dasarnya [7] (root) dengan menghilangkan semua imbuhan kata (affixes) meliputi awalan kata (prefixes), sisipin kata (infixes), akhiran kata (suffixes) dan atau menghilangkan awalan dan akhiran kata (confixes) pada kata turunan. Teks yang sudah dinormalkan, selanjutnya dilakukan stemming menggunankan tool stemmer dari Sastrawi, sebuah library yang ditulis menggunakan Bahasa python.…”

Section: Gambar 1 Metode Penelitianunclassified

Deteksi Emosi Media Sosial Menggunakan Term Frequency- Inverse Document Frequency

Rohman¹,

Handayani²,

Dwi³

et al. 2021

CSRID

View full text Add to dashboard Cite

<em>Pada saat ini, manusia cenderung mengekspresikan pendapat, dan emosi melalui media sosial. Keterbukaan ekspresi pada media sosial membuat batasan batasan pribadi seseorang menjadi lebur. Orang tidak lagi sungkan menulis kehidupan pribadinya melalui postingan status pembaharuan untuk dilihat oleh orang lain. Penulis mencoba menggunakan data dari media sosial agar dapat dilakukan analisis untuk mendapatan informasi kepribadian termasuk emosi. Sebelum dianalisis, data dilakukan pra pemrosesan membuang symbol dan icon, normalisasi teks, stemming dan membuang stopword terlebih dahulu untuk memperbaiki data dari media sosial yang menggunakan bahasa tidak baku. Pra pemrosesan memperoleh hasil akhir 365 dataset yang dipisah menjadi 265 data latih dan 100 data uji. Tiap data sudah memiliki label emosi yang diberikan secara manual oleh pengguna facebook selaku penulis dari postingan. Perhitungan dilakukan dengan TF IDF untuk mendapatkan bobot tiap kata atau token, lalu label emosi data latih dengan nilai tertinggi diberikan pada data yang diuji. Dari 100 data uji diperoleh akurasi 59%, selebihnya 41% tidak akurat. Emosi dianggap hal penting yang berpengaruh pada seseorang dalam pengambilan keputusan, sehingga deteksi emosi seseorang dapat dimanfaatkan sebagai input sistem pendukung keputusan penerimaan pegawai dan konseling kepribadian.</em>

show abstract

Section: Gambar 1 Metode Penelitianunclassified

Deteksi Emosi Media Sosial Menggunakan Term Frequency- Inverse Document Frequency

Rohman¹,

Handayani²,

Dwi³

et al. 2021

CSRID

View full text Add to dashboard Cite

show abstract

“…However, in case there are no human annotated datasets, the majority of people choose to use lexicon based approaches [40]. Thus, extensive research has been done for sentiment analysis using machine learning approaches [41][42][43]. As far as the good results for sentiment analysis are concerned, the two traditional approaches for sentiment analysis can be combined in order to gain the advantages of each approach.…”

Section: Traditional Approaches For Sentiment Analysismentioning

confidence: 99%

Sentiment analysis using deep learning approaches: an overview

Habimana

et al. 2019

Sci. China Inf. Sci.

146

View full text Add to dashboard Cite

show abstract

“…Their solution has been assessed with various languages -English, German, Czech and Spanish. The described learning is fully automatic, can be connected to any language and no complicated preprocessing is needed [10].…”

Section: Background Knowledgementioning

confidence: 99%

Aspect Based Sentiment Analysis using POS Tagging and TFIDF

Srividya¹,

Sowjanya²

2019

IJEAT

View full text Add to dashboard Cite

Social media content on the internet is increasing day by day. Since media knowledge helps people in making decisions, web based businesses give their clients an opportunity to express their opinions about items available on the web in the form of surveys and reviews. Sentiment analysis can be used on product reviews or tweets, comments, blogs to infer individual’s feelings or attitudes. Here Aspect Based Sentiment Analysis is used to extract most interesting aspect of a particular product from unlabeled text. We have developed two models for aspect/feature extraction.Model1 uses POS tagging whereas Model2 utilizes TFIDF .In Model 1 we start with noun phrase algorithm and extend it to adjectives and adverbs to extract all the aspect terms. In model2 after data preprocessing TDIDF technique is used. The relative importances of the aspects are calculated and the most important positive, negative and neutral aspects are presented to the user. Naïve Bayes, Support Vector machine, Decision Tree, KNN were used to classify the sentiment polarity of the generated aspects

show abstract

Sentiment analysis based on Support Vector Machine and Big Data

Cited by 23 publications

References 6 publications

Deteksi Emosi Media Sosial Menggunakan Term Frequency- Inverse Document Frequency

Deteksi Emosi Media Sosial Menggunakan Term Frequency- Inverse Document Frequency

Sentiment analysis using deep learning approaches: an overview

Aspect Based Sentiment Analysis using POS Tagging and TFIDF

Contact Info

Product

Resources

About