Rami Belkaroui - Academia.edu (original) (raw)

Papers by Rami Belkaroui

Recherches en Communication, Apr 9, 2019

académiques présents dans les sources théoriques et scientifiques s'ajustent, se réactualisent à ... more académiques présents dans les sources théoriques et scientifiques s'ajustent, se réactualisent à la lumière des savoirs d'expérience des viticulteurs. Ce travail s'attache également à analyser la nature protéiforme des savoirs d'expérience et à rendre compte de leur pluralité.

Recherches en Communication

Dans le cadre d’un projet FUI initié en octobre 2016 (projet winecloud) visant à construire un ou... more Dans le cadre d’un projet FUI initié en octobre 2016 (projet winecloud) visant à construire un outil de traçabilité et prédictif du cycle de la vigne et du vin, un travail sur la collecte et la nature des savoirs a été nécessaire de manière à penser un système ontologique qui se rapproche le plus du raisonnement du domaine métier. Le présent article vise plus spécifiquement à étudier le cycle de vie de la vigne. Nous rendons compte que les savoirs académiques présents dans les sources théoriques et scientifiques s’ajustent, se réactualisent à la lumière des savoirs d’expérience des viticulteurs. Ce travail s’attache également à analyser la nature protéiforme des savoirs d’expérience et à rendre compte de leur pluralité.

Ingénierie des systèmes d'information

Vietnam Journal of Computer Science

Bound to 140 characters, tweets are short and ambiguous by nature. It can be hard for a user with... more Bound to 140 characters, tweets are short and ambiguous by nature. It can be hard for a user without any kind of context to effectively understand what the tweet is about. Due to this restriction, it is, therefore, necessary to know the tweet's context to make it easily understandable to a reader. In this paper, we treat the problem of tweet contextualization. We propose a specific method allowing to automatically contextualize tweets using information coming from social user interactions. Contrary to classical contextualization methods that only consider text information which is insufficient, since text information on Twitter is very sparse, we combine different types of signals (social, temporal, textual). Our experimental results validate the benefits of our approach and confirm that generated contexts contain relevant information with given tweet.

Procedia Computer Science

Proceedings of the 9th International Conference on Theory and Practice of Electronic Governance - ICEGOV '15-16, 2016

Governments are making considerable efforts in order to enhance citizens' participation in their ... more Governments are making considerable efforts in order to enhance citizens' participation in their decision-making and policy processes. In order to understand the citizens' needs, the decision makers need to know more about citizens' behaviors, preferences and ability to use e-government online services. Recently, social media represents a strategic opportunity that can help governments to become more transparent by providing citizens with better services and enhancing information's access in a way that makes them more involved. In this paper, we propose a new conceptual framework that investigates users and communities' profiles based on social media. The aim of this paper is to explore the social citizens' profiles in order to improve and adapt public services, decision making, information sharing, transparency and collaboration enhancing...to the individual's current and relevant needs.

Advances in Intelligent Systems and Computing, 2015

Today, social media services and multiplatform applications such as microblogs, forums and social... more Today, social media services and multiplatform applications such as microblogs, forums and social networks gives people the ability to communicate, interact and generate content which establish social and collaborative backgrounds. These services now embodies the leading and biggest repository containing millions of Big social Data that can be useful for many applications such as measure public sentiment, trends monitoring, reputation management and marketing campaigns. But social media data are essentially unstructured that's what makes it so interesting and so hard to analyze. Making sense of it and understanding what it means will require all new technologies and techniques, including the emerging field of big data. In addition, social media is a key model of the velocity and variety which are main characteristics of Big Data. In this paper, we propose a new approach to retrieve conversation on microblogging sites that combine Big Data environment and social media analytics solutions. The goal of our approach is to present a more informatives result and solve the information overload problem within Big Data environment. The proposed approach has been implemented and evaluated by comparing it with Google and Twitter Search engines and we obtained very promising results.

Proceedings of the 5th International Conference on Web Intelligence, Mining and Semantics - WIMS '15, 2015

Nowadays, microblogging sites have completely changed the manner in which people communicate and ... more Nowadays, microblogging sites have completely changed the manner in which people communicate and share information. They are among the most relevant source of knowledge where information is created, exchanged and transformed, as witnessed by the important number of their users and their activities during events or campaigns like the terror attack in Paris in 2015. On Twitter, users post messages (called tweets) in real time about events, natural disasters, news, etc. Tweets are short messages that do not exceed 140 characters. Due to this limitation, an individual tweet it's rarely self-content. However, user cannot effectively understand or consume information. In order, to make tweet understandable to a reader, it is therefore necessary to know their context. In fact, on Twitter, context can be derived from users interactions, content streams and friendship. Given that there are rich user interactions on Twitter. In this paper, we propose an approach for tweet contextualization task which combines different types of signals from social users interactions to provide automatically information that explains the tweet. In addition, our approach aims to help users to satisfy any contextual information need. To evaluate our approach, we construct a reference summary by asking assessors to manually select the most informative tweets as a summary. Our experimental results based on this editorial data set offers interesting results and help ensure that context summaries contain adequate correlating information with the given tweet.

Lecture Notes in Computer Science, 2015

In the current era, microblogging sites have completely changed the manner in which people commun... more In the current era, microblogging sites have completely changed the manner in which people communicate and share information. They give users the ability to communicate, interact, create conversations with each other and share information in real time about events, natural disasters, news, etc. On Twitter, users post messages called tweets. Tweets are short messages that do not exceed 140 characters. Due to this limitation, an individual tweet it's rarely self-content. However, users cannot effectively understand or consume information. In order, to make tweets understandable to a reader, it is therefore necessary to know their context. In fact, on Twitter, context can be derived from users interactions, content streams and friendship. Given that there are rich user interactions on Twitter. In this paper, we propose an approach for tweet contextualization task which combines different types of signals from social users interactions to provide automatically information that explains the tweet. To evaluate our approach, we construct a reference summary by asking assessors to manually select the most informative tweets as a summary. Our experimental results based on this editorial data set offers interesting results and ensure that context summaries contain adequate correlating information with the given tweet.

Studies in Computational Intelligence, 2015

Last years, people are becoming more communicative through expansion of services and multi-platfo... more Last years, people are becoming more communicative through expansion of services and multi-platform applications such as blogs, forums and social networks which establishes social and collaborative backgrounds. These services like Twitter, which is the main domain used in our work can be seen as very large information repository containing millions of text messages usually organized into complex networks involving users interacting with each other at specific times. Several works have proposed tools for tweets search focused only to retrieve the most recent but relevant tweets that address the information need. Therefore, users are unable to explore the results or retrieve more relevant tweets based on the content and may get lost or become frustrated by the information overload. In addition, finding good results concerning the given subjects needs to consider the entire context. However, context can be derived from user interactions. In this work, we propose a new method to retrieval conversation on microblogging sites. It's based on content analysis and content enrichment. The goal of our method is to present a more informative result compared to conventional search engine. The proposed method has been implemented and evaluated by comparing it to Google and Twitter Search engines and we obtained very promising results.

2014 Tenth International Conference on Signal-Image Technology and Internet-Based Systems, 2014

With the explosion of Web 2.0, people are becoming more communicative through expansion of servic... more With the explosion of Web 2.0, people are becoming more communicative through expansion of services and multi-platform applications such as microblogs, forums and social networks which establishes social and collaborative backgrounds. These services can be seen as very large information repository containing millions of text messages usually organized into complex networks involving users interacting with each other at specific times. Several works focused only to retrieve separate tweets or those sharing same hashtags, but, it is not powerful enough if the goal of the search is to retrieve relevant tweets based on content. In addition, finding good results concerning the given subjects needs to consider the entire context. However, context can be derived from user interactions. In this work, we propose a new method to retrieval conversation on microblogging sites. It's based on content analysis and content enrichment. The goal of our method is to present a more informative result compared to conventional search engine. To valid our method, we developed the TCOND system (Twitter Conversation Detector) which offers an alternative, results to keyword search on twitter and google. We have evaluated our method on collected social network corpus related to specific subjects, and we obtained good results.