Privacy-preserving topic model for tagging recommender systems

Tagging recommender systems provide users the freedom to explore tags and obtain recommendations. The releasing and sharing of these tagging datasets will accelerate both commercial and research work on recommender systems. However, releasing the original tagging datasets is usually confronted with serious privacy concerns, because adversaries may re-identify a user and her/his sensitive information from tagging datasets with only a little background information. Recently, several privacy techniques have been proposed to address the problem, but most of these lack a strict privacy notion, and rarely prevent individuals being re-identified from the dataset. This paper proposes a privacy- preserving tag release algorithm, PriTop. This algorithm is designed to satisfy differential privacy, a strict privacy notion with the goal of protecting users in a tagging dataset. The proposed PriTop algorithm includes three privacy-preserving operations: Private topic model generation structures the uncontrolled tags; private weight perturbation adds Laplace noise into the weights to hide the numbers of tags; while private tag selection finally finds the most suitable replacement tags for the original tags, so the exact tags can be hidden. We present extensive experimental results on four real-world datasets, Delicious, MovieLens, Last.fm and BibSonomy. While the recommendation algorithm is successful in all the cases, our results further suggest the proposed PriTop algorithm can successfully retain the utility of the datasets while preserving privacy.

Overcoming data scarcity of Twitter: using tweets as bootstrap with application to autism-related topic content analysis

Notwithstanding recent work which has demonstrated the potential of using Twitter messages for content-specific data mining and analysis, the depth of such analysis is inherently limited by the scarcity of data imposed by the 140 character tweet limit. In this paper we describe a novel approach for targeted knowledge exploration which uses tweet content analysis as a preliminary step. This step is used to bootstrap more sophisticated data collection from directly related but much richer content sources. In particular we demonstrate that valuable information can be collected by following URLs included in tweets. We automatically extract content from the corresponding web pages and treating each web page as a document linked to the original tweet show how a temporal topic model based on a hierarchical Dirichlet process can be used to track the evolution of a complex topic structure of a Twitter community. Using autism-related tweets we demonstrate that our method is capable of capturing a much more meaningful picture of information exchange than user-chosen hashtags.

Topic model kernel classification with probabilistically reduced features

Probabilistic topic models have become a standard in modern machine learning to deal with a wide range of applications. Representing data by dimensional reduction of mixture proportion extracted from topic models is not only richer in semantics interpretation, but could also be informative for classification tasks. In this paper, we describe the Topic Model Kernel (TMK), a topicbased kernel for Support Vector Machine classification on data being processed by probabilistic topic models. The applicability of our proposed kernel is demonstrated in several classification tasks with real world datasets. TMK outperforms existing kernels on the distributional features and give comparative results on nonprobabilistic data types.

Morphomettic changes on honeybee Apis mellifera L. workers fat body cells after juvenile hormone topic application at emergence

The effect of topical application of juvenile hormone (JH) over the lifetime of worker bees was evaluated in Apis mellifera, by measuring the area of the two cell types, trophocytes and oenocytes, found in the fat body. Topical application of 1 mu l of a 1 mu g/mu l solution of JH in acetone to the abdomens of newly emerged workers produced an increase in cell size, in both types of cell of 5-day-old treated workers in relation to the untreated control. The treatment was more effective on the oenocytes, since there were significant differences compared to the averages of the treatments and the interaction of the treatments with the age of the workers. The developmental pattern seemed to differ from the treated group. However, subsequent effects were probably dependent on different, natural variations in hormonal levels. (c) 2007 Elsevier Ltd. All rights reserved.

The influence of topic and systemic administration of copaiba oil on the alveolar wound healing after tooth extraction in rats

The Copaiba oil has been used as an auxiliary treatment of inflammations, skin disorders and stomach ulcers, however, in dentistry, this alternative medicine has not been investigated yet. The purpose of this study was to evaluate the influence of topic and systemic administration of copaiba oil on the alveolar wound healing after tooth extraction. Twenty-eight wistar male rats had their lower first molar teeth extracted. Subsequently, they were divided in four groups, according to the treatment performed: (a) alveolar socket irrigation with copaiba oil; (b) alveolar socket irrigation with physiological serum; (c) daily gavage with copaiba oil or (d) daily gavage with physiological serum. After the sacrifice, the mandibles were removed and processed in order to obtain decalcified histological sections. The results demonstrated high level of epithelial migration, small number of inflammatory cells and vascular enhancement in the animals which received systemic administration of copaiba oil. The rats treated with topic administration of copaiba oil presented ulcerations and large number of inflammatory cells. An increased bone neoformation was observed in both groups treated with copaiba oil when compared with placebo group. It could be concluded that topic or systemic administration of copaiba oil leads to a better alveolar bone healing, however the topic application on connective tissue should be carefully considered, regarding the whole socket wound healing. © Medicina Oral S. L. C.I.F. B 96689336 - eISSN: 1989-5488.

Algunas reflexiones sobre la forma de abordar el tema del Area de Libre Comercio de las Américas = Reflections on ways to approach the topic of the Free Trade Areas of the Americas

Incluye Bibliografía

The topic normalized impact factor

[EN] The journal impact factor is not comparable among fields of science because of systematic differences in publication and citation behaviour across disciplines. In this work, a source normalization of the journal impact factor is proposed. We use the aggregate impact factor of the citing journals as a measure of the citation potential in the journal topic, and we employ this citation potential in the normalization of the journal impact factor. An empirical application in a set of 224 journals from four different fields shows that our normalization, using the citation potential in the journal topic, reduces the between-group variance with respect to the within-group variance in a higher proportion than the rest of indicators analysed.

Analisi automatica della corporate reputation attraverso il topic modeling

Questo elaborato tratta dell'importanza dell'analisi testuale tramite strumenti informatici. Presenta la tecnica più utilizzata per questo tipo di analisi il: Topic Modeling. Vengono indicati alcuni degli algoritmi più sfruttati e si descrivono gli obiettivi principali. Inoltre introduce il Web Mining per l’estrazione di informazioni presenti nel web, specificando una tecnica particolare chiamata Web Scraping. Nell'ultima sezione dell’elaborato viene descritto un caso di studio. L’argomento dello studio è la Privatizzazione. Viene suddiviso in tre fasi, la primi riguarda la ricerca dei documenti e articoli da analizzare del quotidiano La Repubblica, nella seconda parte la raccolta di documenti viene analizzata attraverso l’uso del software MALLET e come ultimo passo vengono analizzati i topic, prodotti dal programma, a cui vengono assegnate delle etichette per identificare i sotto-argomenti presenti nei documenti della raccolta.