2017 IEEE International Conference on Information Reuse and Integration (IRI)最新文献_第3页

Predicting the Users' Clickstreams Using Time Series Representation, Symbolic Sequences, and Deep Learning: Application on Job Offers Recommendation Tasks 使用时间序列表示、符号序列和深度学习预测用户点击流:在工作机会推荐任务中的应用

2017 IEEE International Conference on Information Reuse and Integration (IRI) Pub Date : 2017-08-01 DOI: 10.1109/IRI.2017.54

Sidahmed Benabderrahmane, N. Mellouli, M. Lamolle

{"title":"Predicting the Users' Clickstreams Using Time Series Representation, Symbolic Sequences, and Deep Learning: Application on Job Offers Recommendation Tasks","authors":"Sidahmed Benabderrahmane, N. Mellouli, M. Lamolle","doi":"10.1109/IRI.2017.54","DOIUrl":"https://doi.org/10.1109/IRI.2017.54","url":null,"abstract":"During the last decade, the expansion of automatic e-recruitment systems has led to the multiplication of web channels (job boards) that are dedicated to job offers disseminations. In a strategic and economic context where cost control is fundamental, the identification of the relevant job board for a given new job offers has become necessary. The purpose of this work is to present the recent results that we have obtained on a new job board recommendation system that is a decisionmaking tool intended to guide recruiters while they are posting a job on the Internet. First, the job applicant clickstreams history on various job boards are stored in a large learning database, and then represented as time series. Second, a deep neural network architecture is used to predict future values of the clicks on the job boards. Third, and in a parallel way, dimensionality reduction techniques are used to transform the clicks multivariate numerical time series into temporal symbolic sequences. Ngrams are then used to predict future symbols for each sequence. Finally, a list of top ranked job boards are kept by maximizing the clickstreams forecasting in both representations. Our experiments are tested on a real dataset, coming from a job-posting database of an industrial partner. The promising results have shown that using deep learning, the recommendation system outperforms standard multivariate models.","PeriodicalId":254330,"journal":{"name":"2017 IEEE International Conference on Information Reuse and Integration (IRI)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114734469","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Mining Social Media Data Using Topological Data Analysis 利用拓扑数据分析挖掘社交媒体数据

2017 IEEE International Conference on Information Reuse and Integration (IRI) Pub Date : 2017-08-01 DOI: 10.1109/IRI.2017.41

Khaled Almgren, Minkyu Kim, JeongKyu Lee

引用次数: 11

Infusing Latent User-Concerns from User Reviews into Collaborative Filtering 将用户评论中的潜在用户关注点注入协同过滤

2017 IEEE International Conference on Information Reuse and Integration (IRI) Pub Date : 2017-08-01 DOI: 10.1109/IRI.2017.24

Ligaj Pradhan, Chengcui Zhang, Steven Bethard

引用次数: 2

On Using Disparate Scholarly Data to Identify Potential Members for Interdisciplinary Research Groups 利用不同的学术数据来确定跨学科研究小组的潜在成员

2017 IEEE International Conference on Information Reuse and Integration (IRI) Pub Date : 2017-08-01 DOI: 10.1109/IRI.2017.33

F. Osuna, Monika Akbar, A. Gates

引用次数: 1

Predicting Movie Market Revenue Using Social Media Data 利用社交媒体数据预测电影市场收入

2017 IEEE International Conference on Information Reuse and Integration (IRI) Pub Date : 2017-08-01 DOI: 10.1109/IRI.2017.68

Steve Shim, M. Pourhomayoun

{"title":"Predicting Movie Market Revenue Using Social Media Data","authors":"Steve Shim, M. Pourhomayoun","doi":"10.1109/IRI.2017.68","DOIUrl":"https://doi.org/10.1109/IRI.2017.68","url":null,"abstract":"The amount of data being created and processed daily has grown exponentially with the introduction of the internet and social media. While the data are available, there is a struggle to determine how to effectively use and interpret the data. One of the most popular uses for the large quantities of data is to create models to predict the behavior or tendencies. One important application of prediction is predicting financial outcomes using datasets. As a specific case, this study focuses on the use of Twitter data collected leading up to a movie's opening weekend to predict its revenue over the course of each of the opening weekends. Due to the lack of readily available data, the data must be first gathered weekly using Twitter's API and related third party libraries. Construction of the predictive model is based on several machine learning algorithms using a set of features derived from user tweets. The results show that our predictive model can be used to determine the success of movies during the opening weekend by prediction the gross per day value. The modelling and process are presented such that they can be used as an aid to create similar models using other popular social media networks and their data.","PeriodicalId":254330,"journal":{"name":"2017 IEEE International Conference on Information Reuse and Integration (IRI)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127217826","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 13

Knowledge Amplification through Randomization for Scheduling Systems 调度系统随机化中的知识放大

2017 IEEE International Conference on Information Reuse and Integration (IRI) Pub Date : 2017-08-01 DOI: 10.1109/IRI.2017.31

T. Bouabana-Tebibel, S. Rubin, Miled B. Bentaiba, Abdelghani Allaoua, Ahcene Boumhand

引用次数: 2

EARRING: Efficient Authentication of Outsourced Record Matching 耳环:外包记录匹配的有效认证

2017 IEEE International Conference on Information Reuse and Integration (IRI) Pub Date : 2017-08-01 DOI: 10.1109/IRI.2017.16

Boxiang Dong, Wendy Hui Wang

引用次数: 0

On the Verification of UML State Machine Diagrams to Colored Petri Nets Transformation Using Isabelle/HOL 基于Isabelle/HOL的UML状态机图对彩色Petri网转换的验证

2017 IEEE International Conference on Information Reuse and Integration (IRI) Pub Date : 2017-08-01 DOI: 10.1109/IRI.2017.63

Said Meghzili, A. Chaoui, M. Strecker, E. Kerkouche

引用次数: 13

A Multi-stage Approach to Personalized Course Selection and Scheduling 个性化课程选择和排课的多阶段方法

2017 IEEE International Conference on Information Reuse and Integration (IRI) Pub Date : 2017-08-01 DOI: 10.1109/IRI.2017.58

Tyler Morrow, A. Hurson, Sahra Sedigh Sarvestani

引用次数: 8

Heuristics-Based Schema Extraction for Deep Web Query Interfaces 基于启发式的深度Web查询接口模式提取

2017 IEEE International Conference on Information Reuse and Integration (IRI) Pub Date : 2017-08-01 DOI: 10.1109/IRI.2017.80

Chichang Jou, Yucheng Cheng

{"title":"Heuristics-Based Schema Extraction for Deep Web Query Interfaces","authors":"Chichang Jou, Yucheng Cheng","doi":"10.1109/IRI.2017.80","DOIUrl":"https://doi.org/10.1109/IRI.2017.80","url":null,"abstract":"Along with the popularity of the internet, contents inside web databases also increase quickly. These data, hidden behind the query interfaces, are called deep web. These contents normally are not collected by the search engines. Many deep web contents related applications, like contents collection, topic-focused crawling, and data integration, are based on understanding the schema of these query interfaces. The schema needs to cover mappings of input elements and labels, data types of valid input values, and range constraints of the input values. We propose a Heuristics-based deep web query interface Schema Extraction system (HSE) that identifies labels, elements, mappings among labels and elements, and relationships among elements. In HSE, texts surrounding elements are collected as candidate labels. We propose a string similarity function and dynamic similarity threshold setup to cleanse candidate labels. In HSE, elements, candidate labels, and new lines in the query interface are streamlined to produce its Interface Expression (IEXP). By combining the user's view and the designer's view, with the aid of semantic information, we build heuristic rules to extract schema from IEXP of query interfaces in the ICQ dataset. These rules are constructed through utilizing (1) the characteristics of labels and elements, and (2) the spatial, group, and range relationships of labels and elements. Our schema not only helps extracting contents of the deep web, but also benefits the processes of schema matching and schema merging. The experimental results on the TEL-8 dataset show that HSE produces effective performance.","PeriodicalId":254330,"journal":{"name":"2017 IEEE International Conference on Information Reuse and Integration (IRI)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124293564","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0