Recommender Systems

Melville, Prem; Sindhwani, Vikas

doi:10.1007/978-1-4899-7687-1_964

Cited by 139 publications

(151 citation statements)

References 16 publications

Supporting

Mentioning

135

Contrasting

Unclassified

Order By: Relevance

“…searching for something, browsing content) (Steichen et al 2012;Sharma and Singh 2016). Recommender systems tend to fall into one of the following three categories based on which type of information available to the KM system they operate on: (a) content-based filtering, (b) collaborative filtering and (c) hybrids combining elements of both (a) and (b) (Melville and Sindhwani 2010).…”

Section: Background Issuesmentioning

confidence: 99%

HOMER: A semantically enhanced knowledge management approach in the domain of homemade explosives intelligence

Pappas

Paraskakis

2017

Soc. Netw. Anal. Min.

View full text Add to dashboard Cite

This paper presents a new approach, in handling data (encoding, managing and retrieving) in secure sensitive and classified organisations (such as Law Enforcement Agencies (LEAs)), that utilises Web 3.0 technologies as well as knowledge management techniques and pushing of information. This approach signals a departure from current use of databases and pulling of information technologies as well as allowing separation of concerns between how data are organised/structured and how data are manipulated/processed. Such an approach utilises an adaptive knowledge management platform capable of supporting organisational operations of LEAs using data aggregated from assorted, heterogeneous and online sources. Such knowledge is then pushed to the users, using recommenders, in an effortless manner addressing the needs of the organisation. Moreover, the system is designed to afford easier change of operational needs through the addition and removal of multiple folksonomies (representing changes in focus or new trends). These changes are further enriched with semantics providing specialised domain-specific content recommendations and semantically enriched search capabilities. This approach to knowledge retrieval has been applied to the domain of homemade explosives and counter-terrorism efforts as part of the HOMER project, where data are aggregated from sources such as police databases, online forums and explosives wikis. Data are stored in an unstructured manner and annotated by the users, ultimately being categorised as per the knowledge retrieval needs of the organisation, which in this case is to carry out efficient and effective investigations regarding homemade explosives. We describe the architecture of a system that can efficiently and effectively support related investigatory activities, and we also present an evaluation from the perspective of the end-users.

show abstract

Section: Background Issuesmentioning

confidence: 99%

HOMER: A semantically enhanced knowledge management approach in the domain of homemade explosives intelligence

Pappas

Paraskakis

2017

Soc. Netw. Anal. Min.

View full text Add to dashboard Cite

show abstract

“…There are recommendation systems which are available for restaurants (such as zomato app), online dating applications [3], social media application (such as Facebook, LinkedIn, and Twitter) [4] experts, [5] jokes, etc. The recommendation list generated by the recommender system works in two ways through collaborative filtering and [6] content-based filtering.…”

Section: Recommender Systemmentioning

confidence: 99%

Career Recommender: A Novel Approach to Suggest Jobs and Post-Graduation Streams

Mathur

Dixit

Ramanathan

2017

Asian J Pharm Clin Res

View full text Add to dashboard Cite

To implement a novel approach to recommend jobs and colleges based on résumé of freshly graduated students. Job postings are crawled from web using a web crawler and stored in a customized database. College lists are also retrieved for post-graduation streams and stored in a database. Student résumé is stored and parsed using natural language processing methods to form a résumé model. Text mining algorithms are applied on this model to extract useful information (i.e., degree, technical skills, extracurricular skills, current location, and hobbies). This information is used to suggest matching jobs and colleges to the candidate.

show abstract

“…For example, Bain and Boltzmann [8] presented Match Maker, a collaborative filtering friend recommendation system based on personality matching. Kwon and Kim [13] proposed a friend recommendation method using physical and social context. However, the authors did not explain what the physical and social context is and how to obtain the information.…”

Section: Literature Reviewmentioning

confidence: 99%

Survey on an Efficient Method for Finds Friends in Social Networks

2017

IJAERD

View full text Add to dashboard Cite

show abstract

Recommender Systems

Cited by 139 publications

References 16 publications

HOMER: A semantically enhanced knowledge management approach in the domain of homemade explosives intelligence

HOMER: A semantically enhanced knowledge management approach in the domain of homemade explosives intelligence

Career Recommender: A Novel Approach to Suggest Jobs and Post-Graduation Streams

Survey on an Efficient Method for Finds Friends in Social Networks

Contact Info

Product

Resources

About