A CASE STUDY ON THE APPLICATION OF THE MAAEM METHODOLOGY FOR THE SPECIFICATION MODELING OF RECOMMENDER SYSTEMS IN THE LEGAL DOMAIN

2007 ◽  
Keyword(s):  
Recommender Systems ◽  
Legal Domain

Legal document recommendation system: A cluster based pairwise similarity computation

2021 ◽  
pp. 1-13
Author(s):  
Jenish Dhanani ◽  
Rupa Mehta ◽  
Dipti Rana
Keyword(s):  
Recommender Systems ◽  
Recommendation System ◽  
Real Life ◽  
Citation Network ◽  
Search Space ◽  
Pairwise Similarity ◽  
Large Numbers ◽  
Legal Document ◽  
Legal Domain ◽  
Similarity Scores

Legal practitioners analyze relevant previous judgments to prepare favorable and advantageous arguments for an ongoing case. In Legal domain, recommender systems (RS) effectively identify and recommend referentially and/or semantically relevant judgments. Due to the availability of enormous amounts of judgments, RS needs to compute pairwise similarity scores for all unique judgment pairs in advance, aiming to minimize the recommendation response time. This practice introduces the scalability issue as the number of pairs to be computed increases quadratically with the number of judgments i.e., O (n2). However, there is a limited number of pairs consisting of strong relevance among the judgments. Therefore, it is insignificant to compute similarities for pairs consisting of trivial relevance between judgments. To address the scalability issue, this research proposes a graph clustering based novel Legal Document Recommendation System (LDRS) that forms clusters of referentially similar judgments and within those clusters find semantically relevant judgments. Hence, pairwise similarity scores are computed for each cluster to restrict search space within-cluster only instead of the entire corpus. Thus, the proposed LDRS severely reduces the number of similarity computations that enable large numbers of judgments to be handled. It exploits a highly scalable Louvain approach to cluster judgment citation network, and Doc2Vec to capture the semantic relevance among judgments within a cluster. The efficacy and efficiency of the proposed LDRS are evaluated and analyzed using the large real-life judgments of the Supreme Court of India. The experimental results demonstrate the encouraging performance of proposed LDRS in terms of Accuracy, F1-Scores, MCC Scores, and computational complexity, which validates the applicability for scalable recommender systems.

Emotion-Aware Recommender Systems – A Framework and a Case Study

2013 ◽  
pp. 141-150 ◽  
Author(s):  
Marko Tkalčič ◽  
Urban Burnik ◽  
Ante Odić ◽  
Andrej Košir ◽  
Jurij Tasič
Keyword(s):  
Recommender Systems

scholarly journals Deep Learning for Recommender Systems: A Netflix Case Study

AI Magazine ◽  
2022 ◽  
Vol 42 (3) ◽  
pp. 7-18
Author(s):  
Harald Steck ◽  
Linas Baltrunas ◽  
Ehtsham Elahi ◽  
Dawen Liang ◽  
Yves Raimond ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Recommender Systems ◽  
Input Data ◽  
Lessons Learned ◽  
Learning Approaches ◽  
Learning Models ◽  
Learning Methods ◽  
Recommendation Algorithms

Deep learning has profoundly impacted many areas of machine learning. However, it took a while for its impact to be felt in the field of recommender systems. In this article, we outline some of the challenges encountered and lessons learned in using deep learning for recommender systems at Netflix. We first provide an overview of the various recommendation tasks on the Netflix service. We found that different model architectures excel at different tasks. Even though many deep-learning models can be understood as extensions of existing (simple) recommendation algorithms, we initially did not observe significant improvements in performance over well-tuned non-deep-learning approaches. Only when we added numerous features of heterogeneous types to the input data, deep-learning models did start to shine in our setting. We also observed that deep-learning methods can exacerbate the problem of offline–online metric (mis-)alignment. After addressing these challenges, deep learning has ultimately resulted in large improvements to our recommendations as measured by both offline and online metrics. On the practical side, integrating deep-learning toolboxes in our system has made it faster and easier to implement and experiment with both deep-learning and non-deep-learning approaches for various recommendation tasks. We conclude this article by summarizing our take-aways that may generalize to other applications beyond Netflix.

scholarly journals A MULTI CRITERIA RECOMMENDATION MODEL FOR JAUNT

2019 ◽  
Vol XLII-4/W18 ◽  
pp. 879-884
Author(s):  
A. Razavi ◽  
F. Hosseinali
Keyword(s):  
Recommender Systems ◽  
Automated System ◽  
Background Information ◽  
Board Game ◽  
Considerable Time ◽  
Short Term ◽  
The Cost ◽  
Mixed Groups ◽  
The City

Abstract. Nowadays, people in most parts of the world always visit, travel and have fun in their cities or other cities, and they spend considerable time and money in their city or in other cities as a tourist. The existence of an intelligent and automated system that can provide the most suitable recreational and cultural offerings at any time and place, with regard to financial capability and time and transport constraints, as well as individual interests and personalization; has always been felt. Recommender systems can be used to suggest suitable recreational options for the user. The main difference between the recommendation model in this study and the previous models is to focus on the short-term planning of a few hours for one day. Previous models were often based on planning a few days a week or days of the month. Also, the cost factor has been considered in this research, which has been less considered in previous models. We used collaborative filtering based on logistic regression to predict whether a type of places is a proper proposition to a user or not. Our case study is about recommending the board game cafés in the city of Kerman, Iran and the result shows that mixed groups between 15 to 30 years old are the best target and our model can predict if board game café is a good suggestion to different users. We used correlation based recommender systems when board game cafes are a proper suggestion for a user and there are at least two options for the user. In case there is no information about the user and his previous rating, popularity based recommender system can be useful. We also used content based recommender systems to give recommendations by having some background information about previous itineraries of a user and his rating to those.

scholarly journals Ontology-Based Liability Decision Support in the International Maritime Law

2020 ◽  
Author(s):  
Mirna El Ghosh ◽  
Habib Abdulrab
Keyword(s):  
Decision Support ◽  
Conceptual Modeling ◽  
Liability Rule ◽  
Maritime Law ◽  
Legal Rules ◽  
Modeling Process ◽  
Legal Domain ◽  
Core Ontologies ◽  
Procedural Aspect

In this paper, we present an ontology-based liability decision support task in the international maritime law, specifically the domain of carriage of goods by sea. We analyze the liabilities of the involved legal agents (carriers and shippers) in case of loss or damage of goods. Thus, a well-founded legal domain ontology, named CargO-S, is used. CargO-S has been developed using an ontology-driven conceptual modeling process, supported by reusing foundational and legal core ontologies. In this work, we demonstrate the usability of CargO-S to design and implement a set of chained rules describing the procedural aspect of the liabilities legal rules. Finally, we employ these rules in a liability rule-based decision support task using a real case study.

Sign in / Sign up

Export Citation Format

Share Document