Today there is a huge amount of information from a lot of various resources such as World Wide Web, news articles, e-books and emails. On the one hand, human beings face a shortage of time, and on the other hand, due to the social and occupational needs, they need to obtain the most important information from various resources. Automatic text summarization enables us to access the most important content in the shortest possible time. In this paper a query-oriented text summarization technique is proposed by extracting the most informative sentences. To this end, a number of features are extracted from the sentences, each of which evaluates the importance of the sentences from an aspect. In this paper 11 of the best features are extracted from each of the sentences. This paper has shown that use of more suitable features leads to improved summaries generated. In order to evaluate the automatic generated summaries, the ROUGE criterion has been used.

Probabilistic topic models are statistical methods whose aim is to discover the latent structure in a large collection of documents. The intuition behind topic models is that, by generating documents by latent topics, the word distribution for each topic can be modelled and the prior distribution over the topic learned. In this paper we propose to apply this concept by modelling the topics of sentences for the aspect detection problem in review documents in order to improve sentiment analysis systems. Aspect detection in sentiment analysis helps customers effectively navigate into detailed information about their features of interest. The proposed approach assumes that the aspects of words in a sentence form a Markov chain. The novelty of the model is the extraction of multiword aspects from text data while relaxing the bag-of-words assumption. Experimental results show that the model is indeed able to perform the task significantly better when compared with standard topic models.

BackgroundConducting a systematic review requires great screening effort. Various tools have been proposed to speed up the process of screening thousands of titles and abstracts by engaging in active learning. In such tools, the reviewer interacts with machine learning software to identify relevant publications as early as possible. To gain a comprehensive understanding of active learning models for reducing workload in systematic reviews, the current study provides a methodical overview of such models. Active learning models were evaluated across four different classification techniques (naive Bayes, logistic regression, support vector machines, and random forest) and two different feature extraction strategies (TF-IDF and doc2vec). Moreover, models were evaluated across six systematic review datasets from various research areas to assess generalizability of active learning models across different research contexts. MethodsPerformance of the models were assessed by conducting simulations on six systematic review datasets. We defined desirable model performance as maximizing recall while minimizing the number of publications needed to screen. Model performance was evaluated by recall curves, WSS@95, RRF@10, and ATD. ResultsWithin all datasets, the model performance exceeded screening at random order to a great degree.The models reduced the number of publications needed to screen by 91.7% to 63.9%. ConclusionsActive learning models for screening prioritization show great potential in reducing the workload in systematic reviews. Overall, the Naive Bayes + TF-IDF model performed the best.

With the enormous growth of online reviews in Internet, sentiment analysis has received more and more attention in information retrieval and natural language processing community. Up to now there are very few researches conducted on sentiment analysis for Persian documents. This paper considers the problem of sentiment classification for online customer reviews in Persian language. One of the challenges of Persian language is using of a wide variety of declensional suffixes. Another common problem of Persian text is word spacing. In Persian in addition to white space as interwords space, an intra-word space called pseudo-space separates word's part. One more noticeable challenge in customer reviews in Persian language is that of utilizing many informal or colloquial words in text. In this paper we study these challenges by proposing a model for sentiment classification of Persian review documents. The proposed model is based on a lemmatization approach for Persian language and is employed Naive Bayes learning algorithm for classification. Additionally we present a new feature selection method based on the mutual information method to extract the best feature collection from the initial extracted features. Finally we evaluate the performance of the model on a manually gathered collection of cellphone reviews, where the results show the effectiveness of the proposed model.