Analysing the Quality of Association Rules by Computing an Interestingness Measures

Manimaran, J.; Velmurugan, T.

doi:10.17485/ijst/2015/v8i15/76693

Cited by 17 publications

(17 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Secondly, we analysed the data through Association Rule Mining (ARM) [Manimaran and Velmurugan 2015a], which is a method to discover patterns within data based on the frequency of the items. ARM uses the support (frequency) of an item in the dataset, and creates rules based on logical sentences (e.g., A → B) [Agrawal et al 1993].…”

Section: Methods and Toolsmentioning

confidence: 99%

“…ARM uses the support (frequency) of an item in the dataset, and creates rules based on logical sentences (e.g., A → B) [Agrawal et al 1993]. These rules are measured through their confidence and lift [Manimaran and Velmurugan 2015b]. To conduct the analyses and report we analyse rules focused on Narrative and Storytelling with high confidence (> 0.8) and lift ( 1.5).…”

Section: Methods and Toolsmentioning

confidence: 99%

See 1 more Smart Citation

Exploring content game elements to support gamification design in educational systems: narrative and storytelling

Palomino

Toda

Oliveira

et al. 2019

Anais Do XXX Simpósio Brasileiro De Informática Na Educação (SBIE 2019)

View full text Add to dashboard Cite

Several studies on gamification applied to educational systems aim at encouraging students to do certain tasks and improving their learning. According to the literature, most gamification frameworks are structural (e.g. scoring systems, ranking, etc.), with few content-related frameworks. To the best of our knowledge, there is no narrative framework available. Therefore this paper analyses data obtained from a survey about the students' preferred game elements in an educational context, with focus on Association Rules found concerning Narrative and Storytelling elements. We show that Narrative and Storytelling are tightly related and provide insights of their use in groups with other game elements, enabling the creation of gamified strategies based on these aspects.Gamified education has already achieved positive results [Borges et al. 2014, Deterding et al. 2011b, when used concomitantly with traditional methodologies, or as a complement to virtual applications. According to [Smith-Robbins 2011], one can observe some of these elements already present in the traditional methodology. Traditional teaching can be compared to the process of gamification, through a parallel between concepts found in the traditional model, such as grades, groups, and degrees, and game elements such as points, levels, and achievements.Nevertheless, in spite of its advantages, gamification interventions might still sometimes fail to improve students' motivation [Toda et al. 2018]. Thus, we have researched ways to improve the current gamification landscape. One way to provide better gamification recommendations, explored in this paper, is to rely on elements different

show abstract

Section: Methods and Toolsmentioning

confidence: 99%

Section: Methods and Toolsmentioning

confidence: 99%

Exploring content game elements to support gamification design in educational systems: narrative and storytelling

Palomino

Toda

Oliveira

et al. 2019

Anais Do XXX Simpósio Brasileiro De Informática Na Educação (SBIE 2019)

View full text Add to dashboard Cite

show abstract

“…O Apriori identifica as regras de associação entre as variáveis A e B, considerando a frequência com que ocorrem em conjunto e eliminando as regras que estão abaixo dos limites de MinSup e MinConf. Como resultado, são obtidas as regras de associação e as medidas que identificam a correlação e dependência entre as variáveis analisadas [Manimaran and Velmurugan 2015]. As medidas obtidas indicam a frequência de coocorrência (Sup) das duas variáveis (A e B); a frequência de ocorrência somente da variável A (SupA) e da B (SupB); a frequência esperada (SupEsp) de coocorrência das variáveis A e B; e a confiança (Conf), que indica a probabilidade de B ocorrer em função da ocorrência da variável A. Outra medida obtida é o coeficiente de correlação (Phi) que indica a força da relação entre A e B, classificando o nível de correlação [Taylor 1990] como: correlação negativa perfeita (-1); forte correlação negativa (-1.0 a -0.68); moderada correlação negativa (-0.67 a -0.36); fraca ou nenhuma correlação (-0.35 a 0.35); moderada correlação positiva (0.36 a 0.67); forte correlação positiva (0.68 a 1.0); sem correlação (0); correlação positiva perfeita (1).…”

Section: Animoveminer -Framework Propostounclassified

Association rules mining applied in the animal movement exploratory analysis

Fontes¹,

Corrêa²,

Stanzani³

et al. 2019

Anais Do VII Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2019)

View full text Add to dashboard Cite

The animal movement analysis determines the animal behavior, which is the basis for understanding the interaction between species and the environment and to guide actions of preservation and conservation. The challenge is how to explore this movement data, getting indications about how the animal behaves over time and space. In this sense, a framework to animal movement exploratory analysis is presented, that combines algorithms for spatiotemporal data analysis and association rules mining, as a first step to answer questions related to animal behavior. We performed the framework’s evaluation in the exploratory analysis of monitored monkeys (Cebus capucinus) in the Panamá.

show abstract

“…Since, it failed to determine a suitable threshold for averaging algorithm. In [15] designed statistical method to analyze the quality rule of the apriori algorithm in association rule mining for splitting the interesting rules within massive association rules. FP-Growth permitted frequent itemset detection without candidate itemset generation algorithm.…”

Section: Related Workmentioning

confidence: 99%

An Efficient Discrimination Prevention and Rule Protection Algorithms Avoid Direct and Indirect Data Discrimination in Web Mining

Babu¹,

Pushpa²

2018

IJIES

View full text Add to dashboard Cite

Discrimination is one of the most important challenging tasks in web mining due to its many legal and ethical features in social media and enterprise based industries. There are an enormous amount of anti-discrimination measures available to prevent discrimination such as using some features like race, religion, gender, nationality, disability, marital status, and age besides situations like employment and training, access to public services, credit, insurance, etc. Practically, those systems are not possible to use in industries due to large datasets. Indirect discrimination contains a set of rules or techniques which are not explicitly specifying discriminatory features, deliberately or accidentally and could create unfair decisions. Existing systems have low classification accuracy and data loss with high discrimination data detection time. To overcome these limitations, an Efficient Discrimination Prevention and Rule Protection (EDPRP) approach has been proposed for removing the discrimination and protects the rule without damaging the data quality. The proposed system designing pre-processing discrimination prevention approach and specify the different features and represent to deal with direct or indirect discrimination. EDPRP is capable of preventing Indirect and direct discrimination, and it allows automatic and routine collection of large amounts of data from the public. In EDPRP, the discrimination prevention model is based on partial data sets as part of the automated decision making. Based on Experimental evaluations, proposed method improves 8% (percentages) of Support and 8 ms (milliseconds) of Execution Time compared than existing methods.

show abstract

Analysing the Quality of Association Rules by Computing an Interestingness Measures

Cited by 17 publications

References 18 publications

Exploring content game elements to support gamification design in educational systems: narrative and storytelling

Exploring content game elements to support gamification design in educational systems: narrative and storytelling

Association rules mining applied in the animal movement exploratory analysis

An Efficient Discrimination Prevention and Rule Protection Algorithms Avoid Direct and Indirect Data Discrimination in Web Mining

Contact Info

Product

Resources

About