Word Sense Disambiguation for Lexicon-Based Sentiment Analysis

Pamungkas, Endang Wahyu; Putri, Divi Galih Prasetyo

doi:10.1145/3055635.3056578

Cited by 8 publications

(7 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this research, we used FastText pre-trained model as the feature extraction and Random Forest Classifier to classify the sentiment of the user feedbacks. With this approach, we used the SentimentAppReview dataset from [12] which then is classified into positive, neutral, and negative label.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

FastText Word Embedding and Random Forest Classifier for User Feedback Sentiment Classification in Bahasa Indonesia

Gunawan¹,

Young²,

Rusli

2022

Ultimatics

View full text Add to dashboard Cite

User feedback nowadays become a platform for software developer to identify and understand user requirements, preferences, and user’s complaints. It is important for the developer to identify the problem that exist in user feedback. According to software growth, user amount also growth. Read and classify one by one manually are wasting time and energy. As the solution for the problem, sentiment analysis system using Random Forest Classifier which use word embedding as the feature extraction is made to help to classify which feedback is positive, neutral, or negative. Random Forest Algorithm is chosen because it gives the best performance, even its need the larger resources. Furthermore, with word embedding, the words which has semantic or syntactic similarities will be detected. Word embedding does not need stemming and stop word removal, so the context of the sentences keep remains. This research is made to implement word embedding to classify sentiment of user feedbacks using Random Forest Classifier. 70.27% accuracy, 80% precision, 54 recall and 54% F1 score is reached when BYU dataset (200 dimension) as embedding dataset with the train and test ratio 80:20.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Natural language processing (NLP) is a computer science field dealing with human language processing in either text or speech [12]. In this research, preprocessing of user feedback includes the punctuation, remove special character, lowering case, and tokenization.…”

Section: B Natural Language Processingmentioning

confidence: 99%

FastText Word Embedding and Random Forest Classifier for User Feedback Sentiment Classification in Bahasa Indonesia

Gunawan¹,

Young²,

Rusli

2022

Ultimatics

View full text Add to dashboard Cite

show abstract

“…Firstly, in order to correct supposebly misspelled words, we use dictionaries from two sources, one is a digital dictionary of Indonesian language [25] and the other one contains the list of slang words in Indonesian language [26]. Secondly, we collected a portion of the feedback data from previous work which can be found in [11] for training and testing the classification model. The feedback data will be used to train two models, the first one is the one without typo correction and the other implements the typo correction preprocessing step using Levenshtein algorithm.…”

Section: Methodsmentioning

confidence: 99%

“…We use two sentiment labels from the dataset, which tell us whether a feedback text is classified as a positive and negative feedback. Below are some examples of end-user feedback consisted in the dataset [11] that were used in our experiment: a. Positive feedback (241 data):…”

Section: Methodsmentioning

confidence: 99%

“…However, as a language with less resource compared to English, research in processing Indonesian language is very crucial, especially if we consider the huge number of social media and mobile application users in the country. Many researchers in the field have already conducted experiments in text classification, especially sentiment analysis/classification, in Indonesian language [11]- [15]. Based on results from related works of research, our previous works implemented and evaluated the performance and applicability of several methods in classifying text written in Indonesian language, such as Naïve Bayes algorithm to classify application user feedback based on their sentiments and specific feedback categories [16], [17], multilayer perceptron to identify fake news [18], and a comparison of several shallow machine learning methods to classify user feedback based on their categories [19].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing text classification performance by preprocessing misspelled words in Indonesian language

2021

View full text Add to dashboard Cite

Supervised learning using shallow machine learning methods is still a popular method in processing text, despite the rapidly advancing sector of unsupervised methodologies using deep learning. Supervised text classification for application user feedback sentiments in Indonesian Language is one of the applications which is quite popular in both the research community and industry. However, due to the nature of shallow machine learning approaches, various text preprocessing techniques are required to clean the input data. This research aims to implement and evaluate the role of Levenshtein distance algorithm in detecting and preprocessing misspelled words in Indonesian language, before the text data is then used to train a user feedback sentiment classification model using multinomial Naïve Bayes. This research experimented with various evaluation scenarios, and found that preprocessing misspelled words in Indonesian language using the Levenshtein distance algorithm could be useful and showed a promising 8.2% increase on the accuracy of the model's ability to classify user feedback text according to their sentiments.

show abstract