Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : Intelmatics

Perolehan Informasi Kembali (Information Retrieval/IR) Menggunakan Topic Modelling untuk Dataset Tempo Wilda Anggriani; Syandra Sari; Anung B. Ariwibowo; Dedy Sugiarto
Intelmatics Vol. 1 No. 2 (2021): Juli - Desember
Publisher : Penerbitan Universitas Trisakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25105/itm.v1i2.5030

Abstract

In the era of technology as it is today, many technologies and information are growing. The presence of information technology makes it easy for everyone to find information. Usually people use search engines like Google, Yahoo, etc. to find information., many technologies and information are growing. The presence of information technology makes it easy for everyone to find information. Usually people use search engines like Google, Yahoo, etc. to find information.Search engines really help humans to get information. Usually the search engine is one example of information retrieval (Information Retrieval / IR). Documents that produced by search engines are relevant documents based on user requests.In this study, the author implemented the IR process to find relevant documents based on existing queries. The results will be compared with relevant documents from previous research using the same dataset, namely the Tempo dataset from 2000 to 2002. This can find out how far the performance of the method used in this research is based on previous research. The method used in this research is the doc2vec method.From the results obtained using the doc2vec model, the smaller the epoch on the doc2vec model, the smaller the results of the average percentage similarity between the relevant documents produced by the doc2vec model and the relevant documents beforehand. While the results of the percentage similarity average of the doc2vec model are based on the vector size which is after the vector size 30 the result is above 35%. Epoch which produces the highest percentage average is epoch 25 from epoch 25, 50, 75, and 100. Vector size that produces the highest average percentage similarity is vector size 40 from vector size 10, 20, 30, 40, 50, 60, 70, 80, 90, and 100. The highest results of the highest percentage similarity are generated by the doc2vec model that uses epoch 25 and vector size 40 is 41,930. In the era of technology as it is today, many technologies and information are growing. The presence of information technology makes it easy for everyone to find information. Usually people use search engines like Google, Yahoo, etc. to find information., many technologies and information are growing. The presence of information technology makes it easy for everyone to find information. Usually people use search engines like Google, Yahoo, etc. to find information.Search engines really help humans to get information. Usually the search engine is one example of information retrieval (Information Retrieval / IR). Documents that produced by search engines are relevant documents based on user requests.In this study, the author implemented the IR process to find relevant documents based on existing queries. The results will be compared with relevant documents from previous research using the same dataset, namely the Tempo dataset from 2000 to 2002. This can find out how far the performance of the method used in this research is based on previous research. The method used in this research is the doc2vec method.From the results obtained using the doc2vec model, the smaller the epoch on the doc2vec model, the smaller the results of the average percentage similarity between the relevant documents produced by the doc2vec model and the relevant documents beforehand. While the results of the percentage similarity average of the doc2vec model are based on the vector size which is after the vector size 30 the result is above 35%. Epoch which produces the highest percentage average is epoch 25 from epoch 25, 50, 75, and 100. Vector size that produces the highest average percentage similarity is vector size 40 from vector size 10, 20, 30, 40, 50, 60, 70, 80, 90, and 100. The highest results of the highest percentage similarity are generated by the doc2vec model that uses epoch 25 and vector size 40 is 41,930.
Ekstraksi Informasi Menggunakan Named Entity Recognition dan Pembuatan Association Rule Pada Dokumen Direktori Putusan Mahkamah Agung Republik Indonesia Muhammad Rizky Fadila Afgan; Syandra Sari; Anung B. Ariwibowo; Dedy Sugiarto
Intelmatics Vol. 2 No. 1 (2022): Januari-Juni
Publisher : Penerbitan Universitas Trisakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25105/itm.v2i1.5031

Abstract

Land is fundamental to the needs of human life. Humans carry out activities on the ground, so that they are obstructed from getting all human activities both directly and indirectly carried out on the ground. Land is a natural resource that is given by God Almighty to the Indonesian people as national wealth and is a means of meeting all life activities that are important for human life. In this case everyone must need land. Land is often used as a case by disputes, because of the limited area of landInvolved a lot of land The author will extract information in the Directory file Decision Mahkmah Agung is done to produce a named entity taken from the file. PDF extracted. In this study, the author uses the introduction of an entity named (NER Entity Recognition or NER). NER is used to retrieve named entities. After that the author uses the Association Rule to inform data in the form of graphs for analysis Land is fundamental to the needs of human life. Humans carry out activities on the ground, so that they are obstructed from getting all human activities both directly and indirectly carried out on the ground. Land is a natural resource that is given by God Almighty to the Indonesian people as national wealth and is a means of meeting all life activities that are important for human life. In this case everyone must need land. Land is often used as a case by disputes, because of the limited area of land                                Involved a lot of land The author will extract information in the Directory file Decision Mahkmah Agung is done to produce a named entity taken from the file. PDF extracted. In this study, the author uses the introduction of an entity named (NER Entity Recognition or NER). NER is used to retrieve named entities. After that the author uses the Association Rule to inform data in the form of graphs for analysis
Recommendation System for Mental Health Article on Circle Application Gading Sectio Aryoseto; Is Mardianto; Anung B. Ariwibowo
Intelmatics Vol. 3 No. 1 (2023): Januari-Juni
Publisher : Penerbitan Universitas Trisakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25105/itm.v3i1.16343

Abstract

Healthy mental health is a condition when minds are in a state of peace and calm and not disturbed, thus enabling us to enjoy our daily lives with respect for others. In Indonesia, there are quite a number of sufferers of mental health disorders, approximately 19 million people over the age of 15 experience mental and emotional disorders, both at mild to severe levels. These data show that the Indonesian state has not been able to properly address mental health problems and that the existence of a pandemic tends to increase sufferers of mental health disorders, which if left unchecked will have a negative impact. Based on this problem, the Circle application, that focuses on mental health using Android technology that supports self-help with several services, one of which is an article service. The article service in the Circle application requires a recommendation system that can recommend articles according to the mental health conditions experienced by users so that the articles are able to alleviate the mental health problems currently experienced by users. Topic Modeling is an approach to analyze a collection of text documents and group them into topics. Topic Modeling has several methods that can be applied in making topics, one of which is BERTopic. It is a technique that leverages Transformer and c-TF-IDF to create dense clusters, preserving keywords in topic descriptions while making topics easier to interpret. There are 3 important components of the BERTopic algorithm namely Document Embedding, Document Clustering, Topic Representation. This study uses Topic Modeling with the BERTopic method as the baseline for the mental health article recommendation system in the circle application.