Mouna Kacimi

Efficient top-k querying over social-tagging networks

Online communities have become popular for publishing and searching content, as well as for finding and connecting to other users. User-generated content includes, for example, personal blogs, bookmarks, and digital photos. These items can be annotated and rated by different users, and these social tags and derived user-specific scores can be leveraged for searching relevant content and discovering subjectively interesting items. Moreover, the relationships among users can also be taken into consideration for ranking search results, the intuition being that you trust the recommendations of your close friends more than those of your casual acquaintances. Queries for tag or keyword combinations that compute and rank the top-k results thus face a large variety of options that complicate the query processing and pose efficiency challenges. This paper addresses these issues by developing an incremental top-k algorithm with two-dimensional expansions: social expansion considers the strength of relations among users, and semantic expansion considers the relatedness of different tags. It presents a new algorithm, based on principles of threshold algorithms, by folding friends and related tags into the search space in an incremental on-demand manner. The excellent performance of the method is demonstrated by an experimental evaluation on three real-world datasets, crawled from deli.cio.us, Flickr, and LibraryThing.

Exploiting social relations for query expansion and result ranking

Online communities have recently become a popular tool for publishing and searching content, as well as for finding and connecting to other users that share common interests. The content is typically user-generated and includes, for example, personal blogs, bookmarks, and digital photos. A particularly intriguing type of content is user-generated annotations (tags) for content items, as these concise string descriptions allow for reasonings about the interests of the user who created the content, but also about the user who generated the annotations. This paper presents a framework to cast the different entities of such networks into a unified graph model representing the mutual relationships of users, content, and tags. It derives scoring functions for each of the entities and relations. We have performed an experimental evaluation on two real-world datasets (crawled from deli.cio.us and Flickr) where manual user assessments of the query result quality show that our unified graph framework delivers high-quality results on social networks.

Gathering and ranking photos of named entities with high precision, high recall, and diversity

Knowledge-sharing communities like Wikipedia and automated extraction methods like those of DBpedia enable the construction of large machine-processible knowledge bases with relational facts about entities. These endeavors lack multimodal data like photos and videos of people and places. While photos of famous entities are abundant on the Internet, they are much harder to retrieve for less popular entities such as notable computer scientists or regionally interesting churches. Querying the entity names in image search engines yields large candidate lists, but they often have low precision and unsatisfactory recall. Our goal is to populate a knowledge base with photos of named entities, with high precision, high recall, and diversity of photos for a given entity. We harness relational facts about entities for generating expanded queries to retrieve different candidate lists from image search engines. We use a weighted voting method to determine better rankings of an entitys photos. Appropriate weights are dependent on the type of entity (e.g., scientist vs. politician) and automatically computed from a small set of training entities. We also exploit visual similarity measures based on SIFT features, for higher diversity in the final rankings. Our experiments with photos of persons and landmarks show significant improvements of ranking measures like MAP and NDCG, and also for diversity-aware ranking.

HON-P2P: a cluster-based hybrid overlay network for multimedia object management

Multimedia centric P2P must take into consideration the main characteristics and the complex relationships among multimedia objects. In this paper, we propose a cluster-based hybrid overlay network HON-P2P for sharing multimedia content. It consists in clustering peers with similar feature based or semantic properties. We define two types of clustering methods corresponding to the semantic and feature based overlays: semantic clustering and feature based clustering. To improve the information retrieval in the HON-P2P network we propose a multimedia cache management methodology. Semantic multimedia cache and feature based multimedia cache are defined for each type of overlay. Moreover, we study the cache placement possibilities inside the cluster and we propose a cache distribution technique taking into account peers capabilities and range query.

Diversifying search results of controversial queries

Diversifying search results of queries seeking for different view points about controversial topics is key to improving satisfaction of users. The challenge for finding different opinions is how to maximize the number of discussed arguments without being biased against specific sentiments. This paper addresses the issue by first introducing a new model that represents the patterns occurring in documents about controversial topics. Second, proposing an opinion diversification model that uses (1) relevance of documents, (2) semantic diversification to capture different arguments and (3) sentiment diversification to identify positive, negative and neutral sentiments about the query topic. We have conducted our experiments using queries on various controversial topics and applied our diversification model on the set of documents returned by Google search engine. The results show that our model outperforms the native ranking of Web pages about controversial topics by a significant margin.

Anonymous opinion exchange over untrusted social networks

Social networks are the fastest growing Internet applications. They offer the possibility to get in touch with current friends, discover where the old ones are, and make new ones. While these applications are a great enabler for our social life, they are also well known to fall short on privacy. The lack of adequate privacy enhancing technology is particularly important in these applications due to the nature of information they deal with, and the fact that many users are underage. This paper provides a contribution in this direction by presenting a protocol, tailored for social network applications, that allows users to ask and/or submit personal opinions while preserving their anonymity.

MOUNA: mining opinions to unveil neglected arguments

A query topic can be subjective involving a variety of opinions, judgments, arguments, and many other debatable aspects. Typically, search engines process queries independently from the nature of their topics using a relevance-based retrieval strategy. Hence, search results about subjective topics are often biased towards a specific view point or version. In this demo, we shall present MOUNA, a novel approach for opinion diversification. Given a query on a subjective topic, MOUNA ranks search results based on three scores: (1) relevance of documents, (2) semantic diversity to avoid redundancy and capture the different arguments used to discuss the query topic, and (3) sentiment diversity to cover a balanced set of documents having positive, negative, and neutral sentiments about the query topic. Moreover, MOUNA enhances the representation of search results with a summary of the different arguments and sentiments related to the query topic. Thus, the user can navigate through the results and explore the links between them. We provide an example scenario in this demonstration to illustrate the inadequacy of relevance-based techniques for searching subjective topics and highlight the innovative aspects of MOUNA. A video showing the demo can be found in http://www.youtube.com/user/mounakacimi/videos .

Finding images of difficult entities in the long tail

While images of famous people and places are abundant on the Internet, they are much harder to retrieve for less popular entities such as notable computer scientists or regionally interesting churches. Querying the entity names in image search engines yields large candidate lists, but they often have low precision and unsatisfactory recall. In this paper, we propose a principled model for finding images of rare or ambiguous named entities. We propose a set of efficient, light-weight algorithms for identifying entity-specific keyphrases from a given textual description of the entity, which we then use to score candidate images based on the matches of keyphrases in the underlying Web pages. Our experiments show the high precision-recall quality of our approach.

Density-Based Clustering for Similarity Search in a P2P Network

P2P systems represent a large portion of the Internet traffic which makes the data discovery of great importance to the user and the broad Internet community. Hence, the power of a P2P system comes from its ability to provide an efficient search service. In this paper we address the problem of similarity search in a Hybrid Overlay P2P Network which organizes data and peers in a high dimensional feature space. Data and peers are described by a set of features and clustered using a density-based algorithm. We experimentally evaluate the effectiveness of the similarity-search using uniform and zipf data distribution.

Entity and Aspect Extraction for Organizing News Comments

News websites give their users the opportunity to participate in discussions about published articles, by writing comments. Typically, these comments are unstructured making it hard to understand the flow of user discussions. Thus, there is a need for organizing comments to help users to (1) gain more insights about news topics, and (2) have an easy access to comments that trigger their interests. In this work, we address the above problem by organizing comments around the entities and the aspects they discuss. More specifically, we propose an approach for entity and aspect extraction from user comments through the following contributions. First, we extend traditional Named-Entity Recognition approaches, using coreference resolution and external knowledge bases, to detect more occurrences of entities in comments. Second, we exploit part-of-speech tag, dependency tag, and lexical databases to extract explicit and implicit aspects around discussed entities. Third, we evaluate our entity and aspect extraction approach, on manually annotated data, showing that it highly increases precision and recall compared to baseline approaches.