A Novel Recommendation System to Match College Events and Groups to Students

Abstract

With the recent increase in data online, discovering meaningful opportunities can be time-consuming and complicated for many individuals. To overcome this data overload challenge, we present a novel text-content-based recommender system as a valuable tool to predict user interests. To that end, we develop a specific procedure to create user models and item feature-vectors, where items are described in free text. The user model is generated by soliciting from a user a few keywords and expanding those keywords into a list of weighted near-synonyms. The item feature-vectors are generated from the textual descriptions of the items, using modified tf-idf values of the users' keywords and their near-synonyms. Once the users are modeled and the items are abstracted into feature vectors, the system returns the maximum-similarity items as recommendations to that user. Our experimental evaluation shows that our method of creating the user models and item feature-vectors resulted in higher precision and accuracy in comparison to well-known feature-vector-generating methods like Glove and Word2Vec. It also shows that stemming and the use of a modified version of tf-idf increase the accuracy and precision by 2% and 3%, respectively, compared to non-stemming and the standard tf-idf definition. Moreover, the evaluation results show that updating the user model from usage histories improves the precision and accuracy of the system. This recommender system has been developed as part of the Agnes application, which runs on iOS and Android platforms and is accessible through the Agnes website.

FSL-BM: Fuzzy Supervised Learning with Binary Meta-Feature for Classification

“…The definition of meta-knowledge is extracting knowledge from feature representation and also we can define it as perfect feature extraction and pre-selected knowledge from unstructured data [39], [40], [41]. The meta-knowledge or perfect feature extraction allows the deep study of feature for the purpose of more precise knowledge.…”

Knowledge-Based Categorization of Scientific Articles for Similarity Predictions

“…Obtaining generic keywords which may have a greater chance of being indexed in BabelNet is a good solution. Qazanfari et al [26] showed that using lemmas improved the precision and accuracy of their recommendation system. That is why lemmatization is included in both search approaches (i.e., exact and further).…”

Evaluando la similitud semántica en textos cortos usando el contexto relacionado y DISCO

“…Medir la Similitud Semántica Textual (SST) entre oraciones o conceptos es una tarea fundamental en varias aplicaciones del Procesamiento del Lenguaje Natural (PLN), por ejemplo, en Sistemas de Recomendación (SR). Un SR es una subclase de filtrado de información que coleccionan información sobre las preferencias de los usuarios para un conjunto de elementos como películas, canciones, libros, aplicaciones, sitios web, entre otros [1], una vez filtrada la información guían a los usuarios para descubrir productos o servicios en una forma personalizada [2,3]. Otra aplicación de la tarea de SST es para ofrecer explicaciones verbales a partir de un par de oraciones [4], lo cual puede ser aplicado en sistemas de tutorado inteligente [5], en recuperación de información para medir la similitud entre la consulta y textos almacenados en una colección de documentos [6], entre otras aplicaciones.…”