Improving search personalisation with dynamic group formation

Vu, Thanh; Song, Dawei; Willis, Alistair; Tran, Son N.; Li, Jingfei

doi:10.1145/2600428.2609482

Cited by 27 publications

(41 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, it requires expensive manual effort to determine the correct categories for each document. Harvey et al [8] and Vu et al [16] applied a latent topic model (i.e., LDA) to determine these topics. This means that the topic space is determined based purely on relevant documents extracted from query logs and does not require human involvement to define the topics.…”

Section: Related Workmentioning

confidence: 99%

“…As one of the key components in advanced search engines (e.g., Google and Bing), Search Personalisation has attracted increasing attention [1,9,12,15,16,19]. The personalisation is expected to improve the usefulness of search algorithms.…”

Section: Introductionmentioning

confidence: 99%

“…Normally, one of the most common approaches is to represent the profile with the main topics discussed in documents which the user has previously clicked on [1,8,11,16,19]. The topics of a document are often obtained from a humangenerated online ontology, such as the Open Directory Project (ODP) [1,11,19].…”

Section: Introductionmentioning

confidence: 99%

“…Moreover, it requires expensive manual effort to determine the correct categories for each document, as mentioned in [8]. In order to solve this problem, recent approaches [8,16] focus on learning latent topics from the relevant documents, using unsupervised models (i.e., Latent Dirichlet Allocation (LDA) [2]). …”

Section: Introductionmentioning

confidence: 99%

“…We note that the three profiles represent the user interest in different time scales (from short-term to long-term). In order to extract topics from the relevant documents, we employ the same approach proposed in [16] that utilises a topic modelling method (i.e., LDA [2]) to automatically derive latent topics instead of using a human-generated ontology as in [1,11,19].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Temporal Latent Topic User Profiles for Search Personalisation

Willis

Tran

et al. 2015

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. 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.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Temporal Latent Topic User Profiles for Search Personalisation

Willis

Tran

et al. 2015

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

Understanding an enriched multidimensional user relevance model by analyzing query logs

Zhang

Song

et al. 2017

Asso for Info Science & Tech

Self Cite

View full text Add to dashboard Cite

Modeling multidimensional relevance in information retrieval (IR) has attracted much attention in recent years. However, most existing studies are conducted through relatively small-scale user studies, which may not reflect a real-world and natural search scenario. In this article, we propose to study the multidimensional user relevance model (MURM) on large scale query logs, which record users' various search behaviors (e.g., query reformulations, clicks and dwelling time, etc.) in natural search settings. We advance an existing MURM model (including five dimensions: topicality, novelty, reliability, understandability, and scope) by providing two additional dimensions, that is, interest and habit. The two new dimensions represent personalized relevance judgment on retrieved documents. Further, for each dimension in the enriched MURM model, a set of computable features are formulated. By conducting extensive document ranking experiments on Bing's query logs and TREC session Track data, we systematically investigated the impact of each dimension on retrieval performance and gained a series of insightful findings which may bring benefits for the design of future IR systems. IntroductionThere have been numerous attempts (Tombros, Ruthven, & Jose, 2005;Xu & Yin, 2008;Xu & Chen, 2006;Zhang, Zhang, Lease, & Gwizdka, 2014) to understand users' search behaviors when retrieving information with search engines, foe example, relevance judgment, satisfaction or dissatisfaction with search results. Understanding how users conduct relevance judgment and what factors influence users' satisfaction with the search results would help researchers design more effective retrieval models and better evaluation methodologies, aiming to further improve users' search experience.Judging the relevance (or utility) of a retrieved document with respect to a user issued query (representing the user's current information need) is a central task for search engines. A large number of studies (Barry, 1998;Tombros et al., 2005;Xu & Yin, 2008;Xu & Chen, 2006;Zhang et al., 2014) have revealed that there exist a range of complex factors (e.g., topicality, novelty, reliability, understandability, and scope) affecting users' perception of relevance for the retrieved documents. However, the existing work is mainly based on small scale user studies, which may not reflect users' natural search scenarios, and the relevance judgments involved were made in a static way that cannot capture the dynamics of a user's information need, search interest, and habit.To address aforementioned limitations, in this article, we propose to study and understand the multidimensional relevance through analyzing real query logs that record real world user interactions (e.g., query reformulations, clicks, and dwelling time, etc.) with the search engine, as an important supplement to the numerous existing work based on user studies. Specifically, we analyze how different factors affect the users' perception of relevance on retrieved documents within the framework of the Multidi...

show abstract

How Different Features Contribute to the Session Search?

Song

Zhang

et al. 2015

Natural Language Processing and Chinese Computing

View full text Add to dashboard Cite

Improving search personalisation with dynamic group formation

Cited by 27 publications

References 8 publications

Temporal Latent Topic User Profiles for Search Personalisation

Temporal Latent Topic User Profiles for Search Personalisation

Understanding an enriched multidimensional user relevance model by analyzing query logs

How Different Features Contribute to the Session Search?

Contact Info

Product

Resources

About