“…TextRank is an unsupervised method that has been used in many previous work on summarization, either as main or baseline method, because of its proven effectiveness [8]- [11]. Previously, many studies have also been conducted to enhance the performance of the TextRank algorithm for text summarization or keyword extraction, such as using word embedding [12]- [18], term frequency-inverse document frequency (TF-IDF) [19], [20], the combination of 1 gram, 2 gram, and Hidden Markov models [21], knowledge graph sentence embedding and K-means clustering [22], statistical and linguistic features for sentence weighting [23], variation of sentence similarity functions [24], and fine-tuning the hyperparameters [13].…”