Claim Missing Document
Check
Articles

Found 5 Documents
Search
Journal : TELKOMNIKA (Telecommunication Computing Electronics and Control)

Supervised Entity Tagger for Indonesian Labor Strike Tweets using Oversampling Technique and Low Resource Features Ayu Purwarianti; Lisa Madlberger; Mochammad Ibrahim
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 14, No 4: December 2016
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v14i4.3876

Abstract

We propose an entity tagger for Indonesian tweets sent during labor strike events using supervised learning methods. The aim of the tagger is to extract the date, location and the person/organization involved in the strike. We use SMOTE (Synthetic Minority Oversampling Technique) as an oversampling technique and conducted several experiments using Twitter data to evaluate different settings with varying machine learning algorithms and training data sizes. In order to test the low resource features, we also conducted experiments for the system without employing the word list feature and the word normalization. Our results indicated that different treatment of different types of machine learning algorithms with low resource features can lead to a good accuracy score. Here, we tried Naïve Bayes, C4.5, Random Forest and SMO (Sequential Minimal Optimization) algorithms using Weka as the machine learning tools. For the Naïve Bayes, due to the data distribution based of the class probability, the best accuracy was achieved by removing data duplication. For C4.5 and Random Forest, SMOTE gave higher accuracy result compared to the original data and the data with data duplication removal. For SMO, there is no significant difference among various sizes of training data.
Determining Trust Scope Attributes Using Goodness of Fit Test: A Survey Titin Pramiyati; Iping Supriana; Ayu Purwarianti
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 13, No 2: June 2015
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v13i2.649

Abstract

Indonesian, as one of the countries with high number of internet users has the potential to serve as the place with great information resources. However, these resources must be accompanied by the availability of dependable information. Information trustworthiness can be obtained by assessing the confidence level (trust) of the source of information. This can be determined by using trust scope attributes. Hence, in this study, we intended to establish the trust scope attributes by means of utilizing the ones contained in the User Profile provided by social media; in this case Facebook, Google+, Twitter, and Linkedin. We carried out the research by conducting four stages namely data collection, attributes grouping, attribute selection, and surveys. A survey was then distributed to 257 randomly selected respondents (divided into two clusters: civilians and military officers) to seek for their opinions in terms of what attributes were considered to be crucial in defining the believability of an information source. Chi-square Goodness of fit Test was conducted to compare observed data with data we would expect to obtain. The results of the research suggested that there was similar judgment in terms of dictating source of information trustworthiness chosen by the research participants with the attributes provided by trust scope category. In this research, both civilians and military officer clusters concurrently perceived that educational background was the most dependable attribute.
Toward a Framework for Indonesian Medical Question Generator Wiwin Suwarningsih; Iping Supriana; Ayu Purwarianti
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 13, No 1: March 2015
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v13i1.648

Abstract

Question generating is the task of automatically generating questions from various inputs such as raw text, database, or semantic representation. In this paper, we attempt to describe a general framework that could help develop and characterize efforts to medical Indonesian generates questions medical text. We propose a new style of question generation that actively uses sentences within a document as a source of answer. We use manually written rules to perform a sequence of general purpose a syntactic transformation (e.g. identification of keywords or key phrase to NER based on PICO frame) to turn a declarative sentence into questions. The final result of this research is a pattern of question and answer pairs, where the test results show the pattern matching algorithm precision value of 0.101 and a recall of 0.712.
Computing Game and Learning State in Serious Game for Learning Ririn Dwi Agustin; Ayu Purwarianti; Kridanto Surendro; Iping S Suwardi
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 13, No 4: December 2015
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v13i4.2248

Abstract

In order to support the adaptive SGfL, teaching materials must be represented in game component that becomes the target of adaptivity. If adaptive architecture of the game only use game state (GS) to recognize player's state, SGfL require another indicator -learning state (LS)- to identify the learning progress. It is a necessary to formulate computational framework for both states in SGfL.The computational framework was divided into two moduls, macro-strategy and micro-strategy. Macro-strategy control the learning path based on learning map in AND-OR Graph data stucture. This paper focus on the Macro-strategy modul, that using online, direct, and centralized adaptivity method. The adaptivity in game has five components as its target. Based on those targets, eight development models of SGfL concept was enumerated. With similarity and difference analysis toward possibility of united LS and GS in computational framework to implement the nine SGfL concept into design and application, there are three groups of the development models i.e. (1) better united GS and LS, (2) must manage LS and GS as different entity, and (3) can choose whether to be united or not. In the model which is united LS with GS, computing model at the macro-strategy modul use and-or graph and forward chaining. However, in the opposite case, macro-strategy requires two intelligent computing solutions, those are and-or graph with forward chaining to manage LS collaborated with Finite State Automata to manage GS. The proposed computational framework of SGfL was resulted from the similarity and difference analysis toward all possible representations of teaching materials into the adaptive components of the game. It was not dependent of type of learning domain and also of the game genre.
A Novel Part-of-Speech Set Developing Method for Statistical Machine Translation Herry Sujaini; Kuspriyanto Kuspriyanto; Arry Akhmad Arman; Ayu Purwarianti
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 12, No 3: September 2014
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v12i3.79

Abstract

Part of speech (PoS) is one of the features that can be used to improve the quality of statistical-based machine translation. Typically, the language PoS determined based grammar of the language or adopt from other languages PoS. This work aims to formulate a model to developing PoS as linguistic factors to improve the quality of machine translation automatically. The research method using word similarity approach, where we perform clustering of the words contained in a corpus. Further classes will be defined as PoS set obtained for a given language.We evaluated the results of the PoS that defined computational results using machine translation system MOSES as the system by comparing the results of the SMT are using PoS sets generated manually, while the assessment of the system using BLEU method. Language that will be used for evaluation is English as the source language and Indonesian as the target language.
Co-Authors Adhitia, Rama Adhitya, Maulana Krisna Adi Pancoro Afrida Helen Alit Kesatria Mendala Aminuddin, Amir Andri Fachrur Rozie Andria Arisal Antoni, Jefry Arief Rahman Arry Akhmad Arman Arry Akhmad Arman Aswin Juari Dessi Puji Lestari Devi Munandar Diana Permata Sari Diana Sari Dianadewi Riswantini Dwi H. Widyantoro Dwi Hendratmo Widyantoro Ekasari Nugraheni Hadi Saputra Halim, Ismail Syababun Hari Bagus Firdaud Haryono Putro, Ibnu Prastowo Hendradjaja, Bayu Herawati, Neng Ayu Herry Sujaini Herry Sujaini Hibatullah, Muhammad Helmi Imamah Imamah Intan Jelita Saragih Iping S Suwardi Iping Supriana Iping Supriana Iping Supriana Iping Supriana Iping Supriana Iping Supriana Iping Supriana Irfan Afif Iskandar, Yanti Rubiyanti Kridanto Surendro Krishna Aurelio Noviandri KUSPRIYANTO Lisa Madlberger Martalia, Anastasia Mia Mengko, Tati Rajab Miranti Jatnika Riski Mochammad Ibrahim Muh Habibi Haidir Muharram, Arief Purnama Neng Ayu Herawati Nila Nurmala Novi Yusliani Nugraha Priya Utama Prathama, Ubaidillah Ariq Purnomo Husnul Khotimah Putra, Helmy Satria Martha Rama Adhitia Rama Adhitia Rama Adhitia Rifky Raymond, Rifky Ririn Dwi Agustin Ruskanda, Fariska Zakhralativa Samuel Cahyawijaya Saputra, Neva Supanto Supanto Titin Pramiyati Titin Pramiyati Titin Pramiyati Titin Pramiyati Tupamahu, Meldrin Untari Novia Wisesty Utama, Nugraha Priya Wiwin Suwarningsih wiwin suwarningsih Wiwin Suwarningsih Wiwin Suwarningsih Wiwin Suwarningsih Yoga Hanggara Yuhana, Umi Laili Zakiy Firdaus Alfikri Zakiy Firdaus Alfikri