Sentiment Analysis with Word Embedding

Deho, Oscar Blessed; Agangiba, A. William; Aryeh, L. Felix; Ansah, Jeffery

doi:10.1109/icastech.2018.8506717

Cited by 27 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Indeed, the vectors which have the ability to encode the words closer in the vector space are supposed to be an identical meaning. The ‘word2vector’ consists of two different kinds of models, namely, continuous bag of words ( 21 ) and the other one is continuous skip gram ( 22 ). The main idea of the continuous skip gram is to utilize the words to predict its adjoining words ( 23 ).…”

Section: Methodsmentioning

confidence: 99%

Deep-STP: a deep learning-based approach to predict snake toxin proteins by using word embeddings

Zulfiqar,

Guo,

Ahmad

et al. 2024

Front. Med.

View full text Add to dashboard Cite

Snake venom contains many toxic proteins that can destroy the circulatory system or nervous system of prey. Studies have found that these snake venom proteins have the potential to treat cardiovascular and nervous system diseases. Therefore, the study of snake venom protein is conducive to the development of related drugs. The research technologies based on traditional biochemistry can accurately identify these proteins, but the experimental cost is high and the time is long. Artificial intelligence technology provides a new means and strategy for large-scale screening of snake venom proteins from the perspective of computing. In this paper, we developed a sequence-based computational method to recognize snake toxin proteins. Specially, we utilized three different feature descriptors, namely g-gap, natural vector and word 2 vector, to encode snake toxin protein sequences. The analysis of variance (ANOVA), gradient-boost decision tree algorithm (GBDT) combined with incremental feature selection (IFS) were used to optimize the features, and then the optimized features were input into the deep learning model for model training. The results show that our model can achieve a prediction performance with an accuracy of 82.00% in 10-fold cross-validation. The model is further verified on independent data, and the accuracy rate reaches to 81.14%, which demonstrated that our model has excellent prediction performance and robustness.

show abstract

Section: Methodsmentioning

confidence: 99%

Deep-STP: a deep learning-based approach to predict snake toxin proteins by using word embeddings

Zulfiqar,

Guo,

Ahmad

et al. 2024

Front. Med.

View full text Add to dashboard Cite

show abstract

“…Penggunaan algoritma Naïve Bayes dalam sentiment analysis memberikan hasil yang bermacam-macam, tidak ada hasil yang konsisten dan komperhensif untuk jenis data tertentu yang secara tidak langsung memerlukan metode pendamping sehingga dapat diperoleh data yang lebih jelas dan lengkap untuk mendapatkan hasil klasifikasi sentimen yang lebih baik. Dalam penelitian yang dilakukan Oscar B. Deho, dkk [6] diperggunakan Skip-gram yang merupakan varian dari Word2Vec dari teknik ekstraksi Word Embedding dalam meningkatkan akurasi klasifikasi sentimen, hal yang hampir sama juga dilakukan oleh Alif Rizal, dll [7] yang menggunakan Word Embedding Layers dengan dikombinasikan model klasifikasi Long Short-Term Memory Network (LSTM) dalam melakukan klasifikasi sentimen dan mampu menghasilkan nilai precision 80%, nilai recall 81%, fl-score 97% dan accuracy 81% dengan jumlah data yang terbatas, sehingga dapat disimpulkan bahwa teknik ekstraksi Word Embedding mampu meningkatkan akurasi model klasifikasi sentimen.…”

Section: Pendahuluanunclassified

Implementasi Convolution-Augmented Transfomer Berbasis Kecerdasan Buatan dalam Analisis Sentimen Teks Hasil Konversi Suara ke Teks

Utomo,

Wahyudi,

Nalendra

2024

generation

View full text Add to dashboard Cite

Keterbatasan mendapatkan informasi yang dialami penyandang disabilitas menjadikan mereka kurang update terhadap perkembangan yang terjadi sehingga secara tidak langsung mendorong berbagai upaya untuk mendapatkan informasi tanpa mempedulikan sumber dan konteks informasi yang diperoleh, konteks informasi yang diperoleh dalam hal ini berkaitan dengan emosi yang berusaha disampaikan lewat tulisan atau teks informasi, maka perlu dirancang dan diimplementasikan yang mampu mengekstraksi dan menemukan inteprestasi emosi bermuatan positif, negatif atau netral dari teks hasil konversi teknologi Speech to Text, sehingga dapat membantu penderita disabilitas pendengaran dalam memahami konteks dan emosi yang terkandung didalam informasi. Aplikasi Speech to Text yang dikombinasikan dengan metode Conformer berbasis kecerdasan buatan dapat membantu penyandang disabilitas pendengaran untuk memahami sentimen atau emosi dari teks hasil konversi suara. Dengan menggunakan kecerdasan buatan yang tergabung dalam metode Conformer dapat dilakukan klasifikasi sentimen terhadap teks hasil konversi juga dapat dideteksi topik yang disampaikan, sehingga diharapkan dapat dimanfaatkan penyandang disabilitas pendengaran dalam memberikan umpan balik yang tidak menyinggung perasaan dan sesuai topik bahasan.

show abstract

“…Word embedding methods turn words into digital vectors. These vectors include more or less information about the semantics and syntax of the word depending on the model employed and the context in which it was used [37]. There are numerous word embedding strategies available.…”

Section: Documents Containing Imentioning

confidence: 99%

Sentiment Analysis on Moroccan Dialect based on ML and Social Media Content Detection

Errami¹,

Ouassil²,

Rachidi³

et al. 2023

IJACSA

View full text Add to dashboard Cite

As technology continues to evolve, humans tend to follow suit, and currently social media has taken place as the defacto method of communication. As it tends to happen with verbal communication, people express their opinions in written form and through an analysis of their words, one can extract what an individual wants from a product, a topic, or an event. By looking at the emotions expressed in such content, governments, businesses, and people can learn a lot that can help them improve their strategies. Therefore, in this study, we will use different algorithms to improve the Moroccan sentiment classification. The first step is to gather and prepare Moroccan Dialectal Arabic Twitter comments. Then, a lot of different combinations of extraction (n-grams) and weighting schemes (BOW/ TF-IDF) and word embedding for feature construction are applied to get the best classification models. We used Naive Bayes, Random Forests, Support Vector Machines, and Logistic regression and LSTM to classify the data we prepared. Our machine learning approach, which incorporates sentiment analysis, was designed to analyze Twitter comments written in Modern Standard Arabic or Moroccan Dialectal Arabic. As a final benchmark of our paper, we were simply a sliver shy away from the 70% mark in our accuracy by relying on the SVM algorithm. Although not a game-changing result, this was enough to encourage us to continue developing our model further.

show abstract

Sentiment Analysis with Word Embedding

Cited by 27 publications

References 5 publications

Deep-STP: a deep learning-based approach to predict snake toxin proteins by using word embeddings

Deep-STP: a deep learning-based approach to predict snake toxin proteins by using word embeddings

Implementasi Convolution-Augmented Transfomer Berbasis Kecerdasan Buatan dalam Analisis Sentimen Teks Hasil Konversi Suara ke Teks

Sentiment Analysis on Moroccan Dialect based on ML and Social Media Content Detection

Contact Info

Product

Resources

About