Tags are an important information source in Web 2.0. They can be used to describe users’ topic preferences as well as the content of items to make personalized recommendations. However, since tags are arbitrary words given by users, they contain a lot of noise such as tag synonyms, semantic ambiguities and personal tags. Such noise brings difficulties to improve the accuracy of item recommendations. To eliminate the noise of tags, in this paper we propose to use the multiple relationships among users, items and tags to find the semantic meaning of each tag for each user individually. With the proposed approach, the relevant tags of each item and the tag preferences of each user are determined. In addition, the user and item-based collaborative filtering combined with the content filtering approach are explored. The effectiveness of the proposed approaches is demonstrated in the experiments conducted on real world datasets collected from Amazon.com and citeULike website

In this paper, we propose a semantic-aware blocking framework for entity resolution (ER). The proposed framework is built using locality-sensitive hashing (LSH) techniques, which efficiently unifies both textual and semantic features into an ER blocking process. In order to understand how similarity metrics may affect the effectiveness of ER blocking, we study the robustness of similarity metrics and their properties in terms of LSH families. Then, we present how the semantic similarity of records can be captured, measured, and integrated with LSH techniques over multiple similarity spaces. In doing so, the proposed framework can support efficient similarity searches on records in both textual and semantic similarity spaces, yielding ER blocking with improved quality. We have evaluated the proposed framework over two real-world data sets, and compared it with the state-of-the-art blocking techniques. Our experimental study shows that the combination of semantic similarity and textual similarity can considerably improve the quality of blocking. Furthermore, due to the probabilistic nature of LSH, this semantic-aware blocking framework enables us to build fast and reliable blocking for performing entity resolution tasks in a large-scale data environment.

Sentiment analysis is one of the key tasks of natural language understanding. Sentiment Evolution models the dynamics of sentiment orientation over time. It can help people have a more profound and deep understanding of opinion and sentiment implied in user generated content. Existing work mainly focuses on sentiment classification, while the analysis of how the sentiment orientation of a topic has been influenced by other topics or the dynamic interaction of topics from the aspect of sentiment has been ignored. In this paper, we propose to construct a Gaussian Process Dynamic Bayesian Network to model the dynamics and interactions of the sentiment of topics on social media such as Twitter. We use Dynamic Bayesian Networks to model time series of the sentiment of related topics and learn relationships between them. The network model itself applies Gaussian Process Regression to model the sentiment at a given time point based on related topics at previous time. We conducted experiments on a real world dataset that was crawled from Twitter with 9.72 million tweets. The experiment demonstrates a case study of analysing the sentiment dynamics of topics related to the event Brexit.

Sentiment Analysis can help to extract knowledge related to opinions and emotions from user generated text information. It can be applied in medical field for patients monitoring purposes. With the availability of large datasets, deep learning algorithms have become a state of the art also for sentiment analysis. However, deep models have the drawback of not being non human-interpretable, raising various problems related to model's interpretability. Very few work have been proposed to build models that explain their decision making process and actions. In this work, we review the current sentiment analysis approaches and existing explainable systems. Moreover, we present a critical review of explainable sentiment analysis models and discussed the insight of applying explainable sentiment analysis in the medical field.

Real-time Entity Resolution (ER) is the process of matching query records in subsecond time with records in a database that represent the same real-world entity. Indexing techniques are generally used to efficiently extract a set of candidate records from the database that are similar to a query record, and that are to be compared with the query record in more detail. The sorted neighborhood indexing method, which sorts a database and compares records within a sliding window, has been successfully used for ER of large static databases. However, because it is based on static sorted arrays and is designed for batch ER that resolves all records in a database rather than resolving those relating to a single query record, this technique is not suitable for real-time ER on dynamic databases that are constantly updated. We propose a tree-based technique that facilitates dynamic indexing based on the sorted neighborhood method, which can be used for real-time ER, and investigate both static and adaptive window approaches. We propose an approach to reduce query matching times by precalculating the similarities between attribute values stored in neighboring tree nodes. We also propose a multitree solution where different sorting keys are used to reduce the effects of errors and variations in attribute values on matching quality by building several distinct index trees. We experimentally evaluate our proposed techniques on large real datasets, as well as on synthetic data with different data quality characteristics. Our results show that as the index grows, no appreciable increase occurs in both record insertion and query times, and that using multiple trees gives noticeable improvements on matching quality with only a small increase in query time. Compared to earlier indexing techniques for real-time ER, our approach achieves significantly reduced indexing and query matching times while maintaining high matching accuracy.