Weakly supervised joint sentiment-topic detection from text

Sentiment analysis or opinion mining aims to use automated tools to detect subjective information such as opinions, attitudes, and feelings expressed in text. This paper proposes a novel probabilistic modeling framework called joint sentiment-topic (JST) model based on latent Dirichlet allocation (LDA), which detects sentiment and topic simultaneously from text. A reparameterized version of the JST model called Reverse-JST, obtained by reversing the sequence of sentiment and topic generation in the modeling process, is also studied. Although JST is equivalent to Reverse-JST without a hierarchical prior, extensive experiments show that when sentiment priors are added, JST performs consistently better than Reverse-JST. Besides, unlike supervised approaches to sentiment classification which often fail to produce satisfactory performance when shifting to other domains, the weakly supervised nature of JST makes it highly portable to other domains. This is verified by the experimental results on data sets from five different domains where the JST model even outperforms existing semi-supervised approaches in some of the data sets despite using no labeled documents. Moreover, the topics and topic sentiment detected by JST are indeed coherent and informative. We hypothesize that the JST model can readily meet the demand of large-scale sentiment analysis from the web in an open-ended fashion.

A comparative study of bayesian models for unsupervised sentiment detection

This paper presents a comparative study of three closely related Bayesian models for unsupervised document level sentiment classification, namely, the latent sentiment model (LSM), the joint sentiment-topic (JST) model, and the Reverse-JST model. Extensive experiments have been conducted on two corpora, the movie review dataset and the multi-domain sentiment dataset. It has been found that while all the three models achieve either better or comparable performance on these two corpora when compared to the existing unsupervised sentiment classification approaches, both JST and Reverse-JST are able to extract sentiment-oriented topics. In addition, Reverse-JST always performs worse than JST suggesting that the JST model is more appropriate for joint sentiment topic detection.

A Fuzzy Decision Strategy for Topic Identification and Dynamic Selection of Language Models

International audience

Extraction of unexpected rules from Twitter hashtags and its application to sport events

Twitter has become a dependable microblogging tool for real time information dissemination and newsworthy events broadcast. Its users sometimes break news on the network faster than traditional newsagents due to their presence at ongoing real life events at most times. Different topic detection methods are currently used to match Twitter posts to real life news of mainstream media. In this paper, we analyse tweets relating to the English FA Cup finals 2012 by applying our novel method named TRCM to extract association rules present in hash tag keywords of tweets in different time-slots. Our system identify evolving hash tag keywords with strong association rules in each time-slot. We then map the identified hash tag keywords to event highlights of the game as reported in the ground truth of the main stream media. The performance effectiveness measure of our experiments show that our method perform well as a Topic Detection and Tracking approach.

The OpAL System at NTCIR 8 MOAT

The present is marked by the availability of large volumes of heterogeneous data, whose management is extremely complex. While the treatment of factual data has been widely studied, the processing of subjective information still poses important challenges. This is especially true in tasks that combine Opinion Analysis with other challenges, such as the ones related to Question Answering. In this paper, we describe the different approaches we employed in the NTCIR 8 MOAT monolingual English (opinionatedness, relevance, answerness and polarity) and cross-lingual English-Chinese tasks, implemented in our OpAL system. The results obtained when using different settings of the system, as well as the error analysis performed after the competition, offered us some clear insights on the best combination of techniques, that balance between precision and recall. Contrary to our initial intuitions, we have also seen that the inclusion of specialized Natural Language Processing tools dealing with Temporality or Anaphora Resolution lowers the system performance, while the use of topic detection techniques using faceted search with Wikipedia and Latent Semantic Analysis leads to satisfactory system performance, both for the monolingual setting, as well as in a multilingual one.

Feature LDA:a supervised topic model for automatic detection of web API documentations from the web

Web APIs have gained increasing popularity in recent Web service technology development owing to its simplicity of technology stack and the proliferation of mashups. However, efficiently discovering Web APIs and the relevant documentations on the Web is still a challenging task even with the best resources available on the Web. In this paper we cast the problem of detecting the Web API documentations as a text classification problem of classifying a given Web page as Web API associated or not. We propose a supervised generative topic model called feature latent Dirichlet allocation (feaLDA) which offers a generic probabilistic framework for automatic detection of Web APIs. feaLDA not only captures the correspondence between data and the associated class labels, but also provides a mechanism for incorporating side information such as labelled features automatically learned from data that can effectively help improving classification performance. Extensive experiments on our Web APIs documentation dataset shows that the feaLDA model outperforms three strong supervised baselines including naive Bayes, support vector machines, and the maximum entropy model, by over 3% in classification accuracy. In addition, feaLDA also gives superior performance when compared against other existing supervised topic models.

Towards the detection of deception in interactive multimedia environments

A classical application of biosignal analysis has been the psychophysiological detection of deception, also known as the polygraph test, which is currently a part of standard practices of law enforcement agencies and several other institutions worldwide. Although its validity is far from gathering consensus, the underlying psychophysiological principles are still an interesting add-on for more informal applications. In this paper we present an experimental off-the-person hardware setup, propose a set of feature extraction criteria and provide a comparison of two classification approaches, targeting the detection of deception in the context of a role-playing interactive multimedia environment. Our work is primarily targeted at recreational use in the context of a science exhibition, where the main goal is to present basic concepts related with knowledge discovery, biosignal analysis and psychophysiology in an educational way, using techniques that are simple enough to be understood by children of different ages. Nonetheless, this setting will also allow us to build a significant data corpus, annotated with ground-truth information, and collected with non-intrusive sensors, enabling more advanced research on the topic. Experimental results have shown interesting findings and provided useful guidelines for future work. Pattern Recognition

Automatic visual detection of human behavior: a review from 2000 to 2014

Due to advances in information technology (e.g., digital video cameras, ubiquitous sensors), the automatic detection of human behaviors from video is a very recent research topic. In this paper, we perform a systematic and recent literature review on this topic, from 2000 to 2014, covering a selection of 193 papers that were searched from six major scientific publishers. The selected papers were classified into three main subjects: detection techniques, datasets and applications. The detection techniques were divided into four categories (initialization, tracking, pose estimation and recognition). The list of datasets includes eight examples (e.g., Hollywood action). Finally, several application areas were identified, including human detection, abnormal activity detection, action recognition, player modeling and pedestrian detection. Our analysis provides a road map to guide future research for designing automatic visual human behavior detection systems.

Sexueller Missbrauch bei Kindern und Jugendlichen- Aufdeckung, Untersuchung und Erstbetreuung [Sexual abuse of female children and adolescents--detection, examination and primary care].

Epidemiological studies show a prevalence of sexual abuse experience among girls from 14-33%. Although indicators of abuse are unspecific, the combination of several findings may be indicative: Somatic signs may be sexually transmitted diseases, vulvovaginal complaints. Psychosocial nonsexual indicators are abrupt behavioural changes, running away from home, eating disorders. Psychosexual signs are hypersexualisation of the language and behaviour, disturbed body image and gender identity. Indirect evidence of abuse is given not only in cases of old vaginal and anal lesions but also in situations, where deep tears of the hymen in the typical localization at the posterior part can be found. The workup and care for children in whom there is suspicion of abuse but no clear evidence asks for highly competent professionals in a multidisciplinary cooperation including pediatric gynecologists, child psychiatrists, children-protection groups and other specialists to avoid on one hand unjustified destabilisation or even destruction of familial structures but to assure on the other hand, that the child victims are treated and followed after in a short and long term comprehensive medical and psychosocial care.

Development and Preliminary Evaluation of a Rapid Oligochromatographic Assay for Specific Detection of New Human Influenza A H1N1 Virus

A new oligochromatographic assay, Speed-Oligo Novel Influenza A H1N1, was designed and optimized for the specific detection of the 2009 influenza A H1N1 virus. The assay is based on a PCR method coupled to detection of PCR products by means of a dipstick device. The target sequence is a 103-bp fragment within the hemagglutinin gene. The analytical sensitivity of the new assay was measured with serial dilutions of a plasmid that contained the target sequence, and we determined that down to one copy per reaction of the plasmid was reliably detected. Diagnostic performance was assessed with 103 RNAs from suspected cases (40 positive and 63 negative results) previously analyzed with a reference real-time PCR technique. All positive cases were confirmed, and no false-positive results were detected with the new assay. No cross-reactions were observed when other viral strains or clinical samples with other respiratory viruses were tested. According to these results, this new assay has 100% sensitivity and specificity. The turnaround time for the whole procedure was 140 min. The assay may be especially useful for the specific detection of 2009 H1N1 virus in laboratories not equipped with real-time PCR instruments

Testing of Diagnostic Methods for Detection of Influenza Virusfor Optimal Performance in the Context of an Influenza Surveillance Network

Influenza surveillance networks must detect early the viruses that will cause the forthcoming annual epidemics and isolate the strains for further characterization. We obtained the highest sensitivity (95.4%) with a diagnostic tool that combined a shell-vial assay and reverse transcription-PCR on cell culture supernatants at 48 h, and indeed, recovered the strain

Utility of the mini-cog for detection of cognitive impairment in primary care: data from two spanish studies.

Objectives. To study the utility of the Mini-Cog test for detection of patients with cognitive impairment (CI) in primary care (PC). Methods. We pooled data from two phase III studies conducted in Spain. Patients with complaints or suspicion of CI were consecutively recruited by PC physicians. The cognitive diagnosis was performed by an expert neurologist, after formal neuropsychological evaluation. The Mini-Cog score was calculated post hoc, and its diagnostic utility was evaluated and compared with the utility of the Mini-Mental State (MMS), the Clock Drawing Test (CDT), and the sum of the MMS and the CDT (MMS + CDT) using the area under the receiver operating characteristic curve (AUC). The best cut points were obtained on the basis of diagnostic accuracy (DA) and kappa index. Results. A total sample of 307 subjects (176 CI) was analyzed. The Mini-Cog displayed an AUC (±SE) of 0.78 ± 0.02, which was significantly inferior to the AUC of the CDT (0.84 ± 0.02), the MMS (0.84 ± 0.02), and the MMS + CDT (0.86 ± 0.02). The best cut point of the Mini-Cog was 1/2 (sensitivity 0.60, specificity 0.90, DA 0.73, and kappa index 0.48 ± 0.05). Conclusions. The utility of the Mini-Cog for detection of CI in PC was very modest, clearly inferior to the MMS or the CDT. These results do not permit recommendation of the Mini-Cog in PC.

Evaluation of the speed-oligo direct Mycobacterium tuberculosis assay for molecular detection of mycobacteria in clinical respiratory specimens.

We present the first evaluation of a novel molecular assay, the Speed-oligo Direct Mycobacterium tuberculosis (SO-DMT) assay, which is based on PCR combined with a dipstick for the detection of mycobacteria and the specific identification of M. tuberculosis complex (MTC) in respiratory specimens. A blind evaluation was carried out in two stages: first, under experimental conditions on convenience samples comprising 20 negative specimens, 44 smear- and culture-positive respiratory specimens, and 11 sputa inoculated with various mycobacterium-related organisms; and second, in the routine workflow of 566 fresh respiratory specimens (4.9% acid-fast bacillus [AFB] smear positives, 7.6% MTC positives, and 1.8% nontuberculous mycobacteria [NTM] culture positives) from two Mycobacterium laboratories. SO-DMT assay showed no reactivity in any of the mycobacterium-free specimens or in those with mycobacterium-related organisms. Compared to culture, the sensitivity in the selected smear-positive specimens was 0.91 (0.92 for MTC and 0.90 for NTM), and there was no molecular detection of NTM in a tuberculosis case or vice versa. With respect to culture and clinical data, the sensitivity, specificity, and positive and negative predictive values for the SO-DMT system in routine specimens were 0.76 (0.93 in smear positives [1.0 for MTC and 0.5 for NTM] and 0.56 in smear negatives [0.68 for MTC and 0.16 for NTM]), 0.99, 0.85 (1.00 in smear positives and 0.68 in smear negatives), and 0.97, respectively. Molecular misidentification of NTM cases occurred when testing 2 gastric aspirates from two children with clinically but not microbiologically confirmed lung tuberculosis. The SO-DMT assay appears to be a fast and easy alternative for detecting mycobacteria and differentiating MTC from NTM in smear-positive respiratory specimens.

New Granada Medium for detection and identification of group B streptococci.

A methotrexate-containing medium for the detection of beta-hemolytic group B streptococci from clinical specimens on the basis of detection of pigment is described. The medium contained peptone, starch, serum, MgSO4, glucose, pyruvate, methotrexate (as pigment enhancer), phosphate-morpholine-propanesulfonic acid buffer, and selective agents. The recovery of beta-hemolytic group B streptococci was comparable to that obtained with selective broth.

American Cancer Society guideline for the early detection of prostate cancer: update 2010.

In 2009, the American Cancer Society (ACS) Prostate Cancer Advisory Committee began the process of a complete update of recommendations for early prostate cancer detection. A series of systematic evidence reviews was conducted focusing on evidence related to the early detection of prostate cancer, test performance, harms of therapy for localized prostate cancer, and shared and informed decision making in prostate cancer screening. The results of the systematic reviews were evaluated by the ACS Prostate Cancer Advisory Committee, and deliberations about the evidence occurred at committee meetings and during conference calls. On the basis of the evidence and a consensus process, the Prostate Cancer Advisory Committee developed the guideline, and a writing committee drafted a guideline document that was circulated to the entire committee for review and revision. The document was then circulated to peer reviewers for feedback, and finally to the ACS Mission Outcomes Committee and the ACS Board of Directors for approval. The ACS recommends that asymptomatic men who have at least a 10-year life expectancy have an opportunity to make an informed decision with their health care provider about screening for prostate cancer after they receive information about the uncertainties, risks, and potential benefits associated with prostate cancer screening. Prostate cancer screening should not occur without an informed decision-making process. Men at average risk should receive this information beginning at age 50 years. Men in higher risk groups should receive this information before age 50 years. Men should either receive this information directly from their health care providers or be referred to reliable and culturally appropriate sources. Patient decision aids are helpful in preparing men to make a decision whether to be tested.