Abstract Developers use software information sites such as Stack Overflow to get and give information on various subjects. These sites allow developers to label content with tags as a short description. Tags, then, are used to describe, categorize and search the posted content. However, tags might be noisy, and postings may become poorly categorized since people tag a posting based on their knowledge of its content and other existing tags. To keep the content well organized, tag recommendation systems can help users by suggesting appropriate tags for their posted content. In this paper, we propose a tag recommendation scheme that uses the textual content of already tagged postings to recommend suitable tags for newly posted content. Our approach combines multi-label classification and textual similarity techniques to improve the performance of tag recommendation. We evaluate the performance of the proposed scheme on 11 software information sites from the Stack Exchange network. The results show a significant improvement over TagCombine, TagMulRec and FastTagRec, which are well-known tag recommendation systems. On average, the proposed model outperforms TagCombine, TagMulRec and FastTagRec by 26.2, 15.9 and 13.8% in terms of Recall@5 and by 16.9, 12.4 and 9.4% in terms of Recall@10, respectively.

In this paper we propose a new optimization for Apriori-based association rule mining algorithms where the frequency of items can be encoded and treated in a special manner drastically increasing the efficiency of the frequent itemset mining process. An efficient algorithm, called TFI-Apriori, is d eveloped for mining the complete set of frequent itemsets. In the preprocessing phase of the proposed algorithm, the most frequent items from the database are selected and encoded. The TFI-Apriori algorithm then takes advantage of the encoded information to decrease the number of candidate itemsets generated in the mining process, and consequently drastically reduces execution time in candidate generation and support counting phases. Experimental results on actual datasets – databases coming from applications with very frequent items – demonstrate how the proposed algorithm is an order of magnitude faster than the classical Apriori approach without any loss in generation of the complete set of frequent itemsets. Additionally, TFI-Apriori has a smaller memory requirement than the traditional Apriori-based algorithms and embedding this new optimization approach in well-known implementations of the Apriori algorithm allows reuse of existing processing flows.

. Word Sense Disambiguation, which is one of the most challenging problems in the process of machine translation, can be considered as a classification problem. In this paper, we use K-Nearest-Neighbor, as one of the most popular classification methods, as well as some knowledge based resources in order to design a WSD scheme. The success of K-Nearest-Neighbor is tightly dependent on two factors; the features used to represent the context in which an ambiguous word occurs and the distance/similarity measure used for comparison of text vectors. Hence, in the present study, we focus on these two matters. For the first purpose, we extract three sets of features; syntactic features, lexical features and semantic features. In order to produce enriched and useful corpora, we apply preprocessed steps. In this work, we carry out a feature selection process as well as a feature weighting policy in order to fine-tune the classifier. For the second purpose, we try several distance/similarity metrics (rather than one metric) in order to find the most proper one. We also assign and use feature weights and propose a weighted formula for every metric. Moreover, to show that the proposed schemes are not language-dependent, we apply the suggested schemes to two sets of data; English and Persian corpora. The evaluation results, with regards to the feature selection and feature weighting strategies, show that the semantic and syntactic features have a significant effect on the classification ability of the system. The results are also encouraging compared to state of the art.

Abstract One of the major issues in the process of machine translation is the problem of choosing the proper translation for a multi‐sense word referred to as word sense disambiguation (WSD). Two commonly used approaches to this problem are statistical and example‐based methods. In statistical methods, ambiguity resolution is mostly carried out by making use of some statistics extracted from previously translated documents or dual corpora of source and target languages. Example‐based methods follow a similar approach as they also make use of bilingual corpora. However, they perform the task of matching at run‐time (i.e. online matching). In this paper, by looking at the WSD problem from a different viewpoint, we propose a system, which consists of two main parts. The first part includes a data mining algorithm, which runs offline and extracts some useful knowledge about the co‐occurrences of the words. In this algorithm, each sentence is imagined as a transaction in Market Basket Data Analysis problem, and the words included in a sentence play the role of purchased items. The second part of the system is an expert system whose knowledge base consists of the set of association rules generated by the first part. Moreover, in order to deduce the correct senses of the words, we introduce an efficient algorithm based on forward chaining in order to be used in the inference engine of the proposed expert system. The encouraging performance of the system in terms of precision and recall as well as its efficiency will be analysed and discussed through a set of experiments.

Frequent itemset mining over sliding window is an interesting problem and has a large number of applications. Sliding window is a widely used model for frequent itemset mining over data streams due to its capability to handle concept drift, its bounded memory and its low processing time. A sliding window-based algorithm requires an efficient data structure that can be updated as fast as possible when inserting and deleting transactions. Moreover, an innovative computing method is needed to provide the set of frequent patterns (FPs) with a little delay after the user issues a request for the mining results within a window. In this study, an efficient representation of the sliding window named blocked bit sequence is introduced which is aimed to store and maintain the content of the window. Moreover, by a novel technique this representation is exploited for efficiently extracting the set of FPs within the current window. Experimental evaluations on both real-life and synthetic data streams show that the proposed approach is faster than recently proposed algorithms in different phases of data stream mining.

Word sense disambiguation (WSD) can be thought of as the most challenging task in the process of machine translation. Various supervised and unsupervised learning methods have already been proposed for this purpose. In this paper, we propose a new efficient fuzzy classification system in order to b e applied for WSD. In order to optimize the generalization accuracy, we use rule-weight as a simple mechanism to tune the classifier and propose a new learning method to iteratively adjust the weight of fuzzy rules. Through computer simulations on TWA data as a standard corpus, the proposed scheme shows a uniformly good behavior and achieves results which are comparable or better than other classification systems, proposed in the past.

Mining frequent patterns over data streams is an interesting problem due to its wide application area. The researchers in this field have been facing two key challenges, namely reduction in runtime and memory usage. In this study, a novel method for efficient mining of frequent patterns over data s treams is proposed. The method is based on sliding window model which divides the window into a number of panes. This method provides a new sliding window mechanism by utilizing a set of simple short lists. Each list stores related information about an item in the sliding window. The proposed mechanism dynamically adopts itself with the concept change. This method is empirically evaluated against recently proposed pane based sliding window algorithms. Experimental results on synthetically generated and real life data streams show the superiority of the proposed method with multiple orders of magnitude in terms of runtime and memory usage with respect to other pane based sliding window algorithms.