Age and Gender Identification using Stacking for Classification⋆ Notebook for PAN at CLEF 2016

This paper presents our approach of identifying the profile of an unknown user based on the activities of known users. The aim of author profiling task of PAN@CLEF 2016 is cross-genre identification of the gender and age of an unknown user. This means training the system using the behavior of different users from one social media platform and identifying the profile of other user on some different platform. Instead of using single classifier to build the system we used a combination of different classifiers, also known as stacking. This approach allowed us explore the strength of all the classifiers and minimize the bias or error enforced by a single classifier.

Characterizing Human Cysticercosis In Portugal

Abstract text Introduction: Cysticercosis results from the ingestion Taenia solium eggs directly by faecal-oral route or contaminated food or water. While, still considered a leading cause of acquired epilepsy in developed countries, this zoonosis has been controlled or eradicated in industrialized countries due to significant improvements in sanitation, pig rearing and slaughterhouse control systems. Objectives: the health burden of human cysticercosis in Portugal. Material and Metodes: We developed a retrospective study on human neurocysticercosis (NCC) hospitalisations based on the national database resulting from National Health Service (NHS) hospital episodes except those of Madeira and Azores Islands. Results: Between 2006 and 2013 there were 357 hospitalized NCC cases in Portugal. Annual frequency of cases between 2006-2013 kept stable (mean 45). NCC was most frequent in those aged 25-34 years (59; 16,5%) and those >75 years (65; 18,2%). Overall, mean age was 47,3 years (median age 45, standard deviation 41,1, mode 28) and 176 cases were in males (49,3%); no significant differences were observed between age and gender (t-student, p>0,05). In Norte Region cases tended to be older than in Lisboa and Vale do Tejo Region. Conclusions: The Directorate-General of Health established the National Observatory of Cysticercosis and Teniiasis which will define criteria for NCC cases monitoring and surveillance (hospitalized and non-hospitalized cases).

Characterizing human cysticercosis in Portugal 2006-2013

Cysticercosis results from the ingestion Taenia solium eggs directly by faecal-oral route or contaminated food or water. While, still considered a leading cause of acquired epilepsy in developed countries, this zoonosis has been controlled or eradicated in industrialized countries due to significant improvements in sanitation, pig rearing and slaughterhouse control systems. We developed a retrospective study on human neurocysticercosis (NCC) hospitalisations based on the national database resulting from National Health Service (NHS) hospital episodes except those of Madeira and Azores Islands. Between 2006 and 2013 there were 357 hospitalized NCC cases in Portugal. Annual frequency of cases between 2006-2013 kept stable (mean 45). NCC was most frequent in those aged 25-34 years (59; 16,5%) and those >75 years (65; 18,2%). Overall, mean age was 47,3 years (median age 45, standard deviation 41,1, mode 28) and 176 cases were in males (49,3%); no significant differences were observed between age and gender (t-student, p>0,05). In Norte Region cases tended to be older than in Lisboa and Vale do Tejo Region. The Directorate-General of Health established the National Observatory of Cysticercosis and Teniiasis which will define criteria for NCC cases monitoring and surveillance (hospitalized and non-hospitalized cases).

Crossing frontiers between tourism and demography. An empirical analysis based on European travellers’ behaviour

This paper aims to establish possible tourism demand scenarios of European travellers to Portugal based on the relationship with changing population structures. A combination of the EuROBAROMETER report 370 (“Attitudes of Europeans towards Tourism in 2013”) and the cohort-component method for population projections will allow the development of different possible tourism demand scenarios. Following the European report, individuals who travelled in 2013 were most likely to live in a household with two or more individuals. Thus, if elderly couples are together till later in their life and in better physiological shape, it is possible that the number of elderly individuals travelling for tourism purposes will increase in the near future. If we can expect tourists from developing countries to be younger due to their demographic dynamics than those from developed countries, where the ageing population is growing fast, we can expect that the percentage of the elderly among tourists will increase. Furthermore, the 2013 European report found that the combination of socio-demographic variables, such as, age, population, gender, household dimension, country of residence and trip purpose explained tourism demand scenarios for Portugal, confirming that seniors and families evidence a paramount sense of importance for the destination. In the literature there is a lack of discussion about the effects of demography in the future and the role of an ageing population in tourism demand choice patterns. We aim to contribute to filling this gap. Consequently, we strongly believe that this paper contributes to the literature by introducing a new field of discussion about the importance of demographic changes in shaping travel trends.

Crossing frontiers between tourism and demography. An empirical analysis based on European travellers’ behaviour

This paper aims to establish possible tourism demand scenarios of European travellers to Portugal based on the relationship with changing population structures. A combination of the EUROBAROMETER report 370 (“Attitudes of Europeans towards Tourism in 2013”) and the cohort-component method for population projections will allow the development of different possible tourism demand scenarios. Following the European report, individuals who travelled in 2013 were most likely to live in a household with two or more individuals. Thus, if elderly couples are together till later in their life and in better physiological shape, it is possible that the number of elderly individuals travelling for tourism purposes will increase in the near future. If we can expect tourists from developing countries to be younger due to their demographic dynamics than those from developed countries, where the ageing population is growing fast, we can expect that the percentage of the elderly among tourists will increase. Furthermore, the 2013 European report found that the combination of socio-demographic variables, such as, age, population, gender, household dimension, country of residence and trip purpose explained tourism demand scenarios for Portugal, confirming that seniors and families evidence a paramount sense of importance for the destination. In the literature there is a lack of discussion about the effects of demography in the future and the role of an ageing population in tourism demand choice patterns. We aim to contribute to filling this gap. Consequently, we strongly believe that this paper contributes to the literature by introducing a new field of discussion about the importance of demographic changes in shaping travel trends.

Author Profiling using SVMs and Word Embedding Averages — Notebook for PAN at CLEF 2016

In this paper, we describe one of the approaches of the participation of Universidade de Évora. Our approach is similar to usual methods where text is preprocessed, features are extracted, and then used in SVMs with cross validation. The main difference is that features used come from averages of word embeddings, specifically word2vec vectors. Using PAN 2016 dataset, we were able to achieve 44.8% and 68.2% for English age and gender classification respectively. We were also able to achieve 51.3% and 67.1% accuracy for Spanish age and gender classification. Finally, we report 71.9% accuracy for Dutch age classification.

Multilingual author profiling using svms and linguistic features

This paper describes various experiments done to investigate author profiling of tweets in 4 different languages – English, Dutch, Italian, and Spanish. Profiling consists of age and gender classification, as well as regression on 5 different person- ality dimensions – extroversion, stability, agreeableness, open- ness, and conscientiousness. Different sets of features were tested – bag-of-words, word ngrams, POS ngrams, and average of word embeddings. SVM was used as the classifier. Tfidf worked best for most English tasks while for most of the tasks from the other languages, the combination of the best features worked better.

The moderating effect of gender on the relationship between coping and suicide risk in a Portuguese community sample of adults

Background and aims(s): The study evaluated the contribution of coping strategies, based on the Toulousiane conceptualization of coping, to the prediction of suicide risk and tested the moderating effect of gender, controlling for depressive symptoms. Method: A two-time data collection design was used. A community sample of 195 adults (91 men and 104 women) ranging in age from 19 to 65 years and living in several Portuguese regions, mostly in Alentejo, participated in this research. Results: Gender, depressive symptoms, control, and withdrawal and conversion significantly predicted suicide risk and gender interacted with control, withdrawal and conversion, and social distraction in the prediction of suicide risk. Coping predicted suicide risk only for women. Conclusions: Results have important implications for assessment and intervention with suicide at-risk individuals. In particular,the evaluation and development of coping skills is indicated as a goal for therapists having suicide at-risk women as clients.