“…Although NLP research on Somali is limited, a few notable studies have emerged in recent years. These studies have primarily focused on basic NLP tasks like part-of-speech tagging and named entity recognition, with a primary emphasis on developing linguistic resources [15], [16] and annotated datasets. However, sentiment analysis for the Somali language remains largely unexplored.…”
Section: Existing Approaches For Somali Language Nlpmentioning
confidence: 99%
“…Somali, with approximately 35 million speakers worldwide, is one such under-resourced language that lacks comprehensive linguistic datasets [15], [16] and NLP tools. The Somali language poses unique challenges for sentiment analysis, necessitating the exploration of novel methodologies that are tailored to the specific linguistic characteristics and limited resources of the language [15], [16].…”
Section: Introduction 11 Background and Motivationmentioning
Sentiment analysis, a fundamental task in natural language processing (NLP), plays a crucial role in understanding people's opinions and emotions expressed in textual data. While sentiment analysis has been extensively studied for major languages, under-resourced languages like Somali have received limited attention in this domain. This paper aims to address this research gap by proposing a resource light approach for sentiment analysis in Somali, which is tailored to the language's unique characteristics and limited linguistic resources. We present a methodology that combines lexicon-based methods and feature engineering techniques to effectively extract sentiment information from Somali text. A sentiment-annotated dataset was created through crowdsourcing, enabling the training and evaluation of a sentiment classification model specifically designed for Somali. Experimental results demonstrate the competitive performance of our approach compared to existing sentiment analysis techniques for under resourced languages. The findings highlight the feasibility of sentiment analysis in Somali, even with a small-scale dataset, and shed light on the implications for sentiment analysis in other under-resourced languages. This research contributes to the advancement of sentiment analysis capabilities for under resourced languages, empowering researchers and practitioners to gain insights from sentiment information in diverse linguistic contexts.
“…Although NLP research on Somali is limited, a few notable studies have emerged in recent years. These studies have primarily focused on basic NLP tasks like part-of-speech tagging and named entity recognition, with a primary emphasis on developing linguistic resources [15], [16] and annotated datasets. However, sentiment analysis for the Somali language remains largely unexplored.…”
Section: Existing Approaches For Somali Language Nlpmentioning
confidence: 99%
“…Somali, with approximately 35 million speakers worldwide, is one such under-resourced language that lacks comprehensive linguistic datasets [15], [16] and NLP tools. The Somali language poses unique challenges for sentiment analysis, necessitating the exploration of novel methodologies that are tailored to the specific linguistic characteristics and limited resources of the language [15], [16].…”
Section: Introduction 11 Background and Motivationmentioning
Sentiment analysis, a fundamental task in natural language processing (NLP), plays a crucial role in understanding people's opinions and emotions expressed in textual data. While sentiment analysis has been extensively studied for major languages, under-resourced languages like Somali have received limited attention in this domain. This paper aims to address this research gap by proposing a resource light approach for sentiment analysis in Somali, which is tailored to the language's unique characteristics and limited linguistic resources. We present a methodology that combines lexicon-based methods and feature engineering techniques to effectively extract sentiment information from Somali text. A sentiment-annotated dataset was created through crowdsourcing, enabling the training and evaluation of a sentiment classification model specifically designed for Somali. Experimental results demonstrate the competitive performance of our approach compared to existing sentiment analysis techniques for under resourced languages. The findings highlight the feasibility of sentiment analysis in Somali, even with a small-scale dataset, and shed light on the implications for sentiment analysis in other under-resourced languages. This research contributes to the advancement of sentiment analysis capabilities for under resourced languages, empowering researchers and practitioners to gain insights from sentiment information in diverse linguistic contexts.
“…Dengan menggunakan algoritma KMP, pencocokan string dapat berjalan secara efisien dan mengurangi jumlah perbandingan yang diperlukan, sehingga meningkatkan kinerja dan kecepatan proses pencarian string. (Sunarto, 2018) (Jimale, 2018).…”
Perkembangan teknologi yang pesat berpengaruh pada semua manusia. Manusia dituntut untuk dapat cerdas mengikuti perkembangan jaman. Perkembangan tersebut selalu berhubungan dengan teknologi informasi yang semakin canggih, baik dari segi perangkat yang digunakan maupun sistem informasinya. Internet dapat menjadi jembatan untuk dapat berkembang. Dalam pelayanan menangani keluhan dari UPT Stasiun Meteorologi Penerbangan kepada bagian terkait yang berada di kantor pusat masih menggunakan whatsapp dan telegram sebagai sarana komunikasi dan pelaporan kendala oleh bagian terkait. Permasalahan yang terjadi oleh sistem tiketing saat ini adalah semakin banyaknya pelaporan oleh UPT Stasiun Meteorologi Penerbangan menggunakan whatsapp dan telegram dinilai kurang maksimal karena sulit melakukan kontrol tiket sehingga dirasa kurang efektif dan efisien. Selain itu dikarenakan banyak tiket yang menumpuk menjadi penyebab terlambatnya penanganan masalah yang melebihi dari waktu estimasi. Berdasarkan latar belakang diatas perlu dilakukan penelitian untuk Meningkatkan Kinerja Helpdesk pada BMKG Pusat Meteorologi Penerbangan. Penelitian menggunakan Pendekatan Knowledge Management System Berbasis Framework Laravel dan Container. Penelitian menggunakan algoritma Knuth Morris Pratt. Fitur yang digunakan adalah pembuatan tiket pelaporan permasalahan di UPT Stasiun Meteorologi Penerbangan. Data yang akan digunakan adalah data cuaca, gempa bumi, iklim dan permasalahan di UPT Stasiun Meteorologi Penerbangan. Sistem telah mampu mengatasi kekurangan-kekurangan yang ada pada BMKG Penerbangan terkait proses pelaporan permasalahan.
“…The Knuth-Morris-Pratt algorithm is used, along with a corpus, to make a spell checker for the Somali language. The KMP algorithm is used in the processing stage to produce suggestion lists for the misspelled words [19]. This algorithm increases the speed of pattern matching between misspelled words and Somali words found in the corpus.…”
During the COVID-19 pandemic time, it is a requirement to deliver online learning since students can not have face-to-face meetings and they depend on gadgets such as a computer, mobile phone, iPad, and laptop to continue their study. One of the subjects is local language learning as this subject is a requirement in some provinces in Indonesia as a gesture concerning local wisdom. However, there is a lack of support for learning the local language since the local languages have a mouth to mouth learning knowledge without any dictionary support. This paper proposed the idea of using the Knuth-Morris-Pratt algorithm to translate the Palembang language to Bahasa Indonesia to help students to learn the Palembang language with the application.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.