Penerapan Metode Association Rule Mining untuk Asosiasi Ulasan Terhadap Aspek Tempat Wisata Jawa Timur Park 3

<p class="Abstrak">Google Review pada salah satu fitur Google Maps dapat menjadi salah satu media untuk mengukur tingkat kepuasan pengunjung Jawa Timur Park 3 (Jatim Park 3). Akan tetapi jumlah ulasan yang mencapai ribuan dan belum tersedianya media pengelola data ulasan dapat mempersulit manajemen Jatim Park 3 dalam mengeksplorasi dan menganalisis masukan pengunjung secara mendetail. Penelitian ini memanfaatkan teknik <em>Association Rule Mining </em>(ARM) dalam mengelola data ulasan sehingga dapat menemukan hubungan kata yang sering muncul pada ulasan. Teknik ini paling populer untuk menemukan hubungan tersembunyi antar variabel. Algoritma yang digunakan dalam mengimplementasikannya adalah algoritma Apriori karena dianggap paling efisien. Pada penelitian ini menggunakan data ulasan sebanyak 1067 ulasan dalam Bahasa Indonesia dari bulan Januari sampai bulan April tahun 2019. Berdasarkan wawancara, data tersebut digolongkan menjadi 8 aspek berdasarkan kata kunci yang sudah ditentukan sebelumnya. Aspek tersebut antara lain akses jalan, biaya, kebersihan, kepuasan, keramaian, pelayanan, keamanan, dan teknologi. Pengujian dilakukan untuk mengetahui pengaruh <em>minimum support</em> dan <em>minimum confidence</em> terhadap <em>rule</em> yang terbentuk. Keseluruhan aspek mampu menghasilkan asosiasi kata dengan algoritma Apriori. Selain itu, Keseluruhan <em>rule</em> yang terbentuk menghasilkan rata-rata <em>lift ratio</em> di atas 1 dimana rule dengan nilai lift ratio diatas 1 tersebut merupakan rule yang unik diantara rule-rule lain yang terebentuk dari asosiasi tersebut. Pada penelitian ini, rule yang terbentuk divisualisasikan untuk menampilkan keterkaitan antara kata kunci dengan aspek pada data ulasan pengunjung Jatim Park 3. Penelitian ini mencoba menggali informasi mengenai pemetaan layanan mana saja yang mendapatkan perhatian pengunjung di Jatim Park 3.</p><p class="Abstrak" align="center"> </p><p class="Judul2"><strong><em>Abstract</em></strong></p><p class="Judul2"> <em>Google Review, which is one of the features of Google Maps can be a medium to measure the satisfaction rate visitors of Jawa Timur Park 3 (Jatim Park 3). the number of reviews that reached thousands and media of review data manager is not available yet complicate the management of Jatim Park to explore and analyze visitor feedback in detail. The Association Rule Mining (ARM) technique is a text mining method that can support the knowledge discovery process in large document collections. ARM is able to link keywords to comments to find words that appear frequently. This technique is most popular for finding hidden relationships between variables. The algorithm used in this study is apriori algorithm because it is the most efficient. In this study, there are 1067 reviews of the visitors in Indonesian from January to April 2019 as the data. The data is classified into 8 aspects based on predetermined keywords. These aspects include road access, cost, cleanliness, satisfaction, hustle, service, security, and technology. Testing was conducted to determine the minimum support and minimum confidence impact of the established rules. The whole aspects is capable of generating word associations with an Apriori algorithm. In addition, the overall rules that are formed produce an average lift ratio above 1 where the rule with that value is a unique rule among other rules formed from the association. In this study, the rules that are formed are visualized to show the relationship between keywords and aspects of visitor reviews of Jatim Park 3. This research tries to dig up information about mapping which services get the attention of visitors in Jatim Park 3.</em></p>

Bongard Problems: A Topological Data Analysis Approach

Bongard problems are a set of 100 visual puzzles posed by M. M. Bongard, where each puzzle consists of twelve images separated into two groups of six images. The task is to find the unique rule separating the two classes in each given problem. The problems were first posed as a challenge for the AI community to test machines ability to imitate complex, context-depending thinking processes using only minimal information. Although some work was done to solve these problems, none of the previous approaches could automatically solve all of them. The present paper is a contribution to attack these problems with a different approach, combining the tools of persistent homology alongside with machine learning methods. In this work, we present an algorithm and show that it is able to solve problems involving differences in connectivity and size as examples, we also show that it can solve problems involving a much larger set of differences provided the right G-equivariant operators

ALLOCATION OF FIXED COSTS: CHARACTERIZATION OF THE (DUAL) WEIGHTED SHAPLEY VALUE

The weighted value was introduced by Shapley in 1953 as an asymmetric version of his value. Since then several axiomatizations have been proposed including one by Shapley in 1981 specifically addressed to cost allocation, a context in which weights appear naturally. It was at the occasion of a comment in which he only stated the axioms. The present paper offers a proof of Shapley's statement as well as an alternative set of axioms. It is shown that the value is the unique rule that allocates additional fixed costs fairly: only the players who are concerned contribute to the fixed cost and they contribute in proportion to their weights. A particular attention is given to the case where some players are assigned a zero weight.

Rule discovery in phonological acquisition

ABSTRACTMenn has suggested that most early phonological rules have the effect of reducing the variety of the child's phonetic output forms. This proposal is compatible with the Interactionist–Discovery (I–D) theory of phonological acquisition. This paper presents one child's unique phonological rule which increases output variety and yet still yields a mismatch with the adult form. Evidence is presented which indicates that the rule was a stable and productive part of the child's phonology and that it was both phonetically and phonologically motivated. It is argued that an addition to the early strategies described by Menn is needed to account, specifically, for the discovery of this unique rule and, generally, for later stages of phonological development.