Thanh Vu

Improving search personalisation with dynamic group formation

Recent research has shown that the performance of search engines can be improved by enriching a users personal profile with information about other users with shared interests. In the existing approaches, groups of similar users are often statically determined, e.g., based on the common documents that users clicked. However, these static grouping methods are query-independent and neglect the fact that users in a group may have different interests with respect to different topics. In this paper, we argue that common interest groups should be dynamically constructed in response to the users input query. We propose a personalisation framework in which a user profile is enriched using information from other users dynamically grouped with respect to an input query. The experimental results on query logs from a major commercial web search engine demonstrate that our framework improves the performance of the web search engine and also achieves better performance than the static grouping method.

Sentiment Classification on Polarity Reviews: An Empirical Study Using Rating-based Features

We present a new feature type named rating-based feature and evaluate the contribution of this feature to the task of document-level sentiment analysis. We achieve state-of-the-art results on two publicly available standard polarity movie datasets: on the dataset consisting of 2000 reviews produced by Pang and Lee (2004) we obtain an accuracy of 91.6% while it is 89.87% evaluated on the dataset of 50000 reviews created by Maas et al. (2011). We also get a performance at 93.24% on our own dataset consisting of 233600 movie reviews, and we aim to share this dataset for further research in sentiment polarity analysis task.

Temporal latent topic user profiles for search personalisation

The performance of search personalisation largely depends on how to build user profiles effectively. Many approaches have been developed to build user profiles using topics discussed in relevant documents, where the topics are usually obtained from human-generated online ontology such as Open Directory Project. The limitation of these approaches is that many documents may not contain the topics covered in the ontology. Moreover, the human-generated topics require expensive manual effort to determine the correct categories for each document. This paper addresses these problems by using Latent Dirichlet Allocation for unsupervised extraction of the topics from documents. With the learned topics, we observe that the search intent and user interests are dynamic, i.e., they change from time to time. In order to evaluate the effectiveness of temporal aspects in personalisation, we apply three typical time scales for building a long-term profile, a daily profile and a session profile. In the experiments, we utilise the profiles to re-rank search results returned by a commercial web search engine. Our experimental results demonstrate that our temporal profiles can significantly improve the ranking quality. The results further show a promising effect of temporal features in correlation with click entropy and query position in a search session.

Search personalization with embeddings

Recent research has shown that the performance of search personalization depends on the richness of user profiles which normally represent the user’s topical interests. In this paper, we propose a new embedding approach to learning user profiles, where users are embedded on a topical interest space. We then directly utilize the user profiles for search personalization. Experiments on query logs from a major commercial web search engine demonstrate that our embedding approach improves the performance of the search engine and also achieves better search performance than other strong baselines.

Modelling Time-aware Search Tasks for Search Personalisation

Recent research has shown that mining and modelling search tasks helps improve the performance of search personalisation. Some approaches have been proposed to model a search task using topics discussed in relevant documents, where the topics are usually obtained from human-generated online ontology such as Open Directory Project. A limitation of these approaches is that many documents may not contain the topics covered in the ontology. Moreover, the previous studies largely ignored the dynamic nature of the search task; with the change of time, the search intent and user interests may also change. This paper addresses these problems by modelling search tasks with time-awareness using latent topics, which are automatically extracted from the tasks relevance documents by an unsupervised topic modelling method (i.e., Latent Dirichlet Allocation). In the experiments, we utilise the time-aware search task to re-rank result list returned by a commercial search engine and demonstrate a significant improvement in the ranking quality.

Improving Text-Based Image Search with Textual and Visual Features Combination

With the huge number of available images on the web, an effective image retrieval system has been more and more needed. Improving the performance is one of crucial tasks in modern text-based image retrieval systems such as Google Image Search, Frickr, etc. In this paper, we propose a unified framework to cluster and re-rank returned images with respect to an input query. However, owning to a difference to previous methods of using only either textual or visual features of an image, we combine the textual and visual features to improve search performance. The experimental results show that our proposed model can significantly improve the performance of a text-based image search system (i.e. Flickr). Moreover, the performance of the system with the combination of textual and visual features outperforms the performance of both the textual-based system and the visual-based system.