Learning to Recommend Related Entities to Search Users

Bi, Bin; Ma, Hao; Hsu, Bo-June; Chu, Wei; Wang, Kuansan; Cho, Junghoo

doi:10.1145/2684822.2685304

Cited by 28 publications

(16 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The authors use SVM to identify newsworthy messages on Twitter based on a manually annotated dataset. Very recently, two workshops have been held focusing on the use of data/text mining techniques to help journalists in their work: Natural Language Processing meets Journalism@EMNLP'17 1 and Data Science + Journalism@KDD'17 2 . All these contributions are concerned more with the design of interfaces to help journalists in digging into trending topics or detecting related contents, than with providing prospective information of possibly interesting new topics to deal with.…”

Section: Related Workmentioning

confidence: 99%

“…A more weakly related research area is entity recommendation, a recommendation engine that links a users' query to a named entity, to help them exploring other topics related to an initial interest. In [1] the authors use a probabilistic three-way Entity Model to provide personalized entity recommendation using three data sources: a knowledge base, search click logs, and entity pane logs. In [2] it is described Spark, a semantic search assistant that links a user's initial query (extracted from Yahoo!)…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A topic recommender for journalists

et al. 2018

View full text Add to dashboard Cite

The way in which people acquire information on events and form their own opinion on them has changed dramatically with the advent of social media. For many readers, the news gathered from online sources become an opportunity to share points of view and information within micro-blogging platforms such as Twitter, mainly aimed at satisfying their communication needs. Furthermore, the need to deepen the aspects related to news stimulates a demand for additional information which is often met through online encyclopedias, such as Wikipedia. This behaviour has also influenced the way in which journalists write their articles, requiring a careful assessment of what actually interests the readers. The goal of this paper is to present a recommender system, What to Write and Why, capable of suggesting to a journalist, for a given event, the aspects still uncovered in news articles on which the readers focus their interest. The basic idea is to characterize an event according to the echo it receives in online news sources and associate it with the corresponding readers' communicative and informative patterns, detected through the analysis of Twitter and Wikipedia, respectively. Our methodology temporally aligns the results of this analysis and recommends the concepts that emerge as topics of interest from Twitter and Wikipedia, either not covered or poorly covered in the published news articles.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

A topic recommender for journalists

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Rather than suggesting entities related to a given input entity, in this section we discuss methods that provide personalized entity recommendations based on the user's current search session. A number of approaches have been proposed for learning models for specific domains, such as movies or celebrities [8,57]. Such model-based methods rely on manually designed domain-dependent features, related to specific properties of entities (e.g., the genre of a movie or how many pop singers were viewed by a specific user).…”

Section: Personalized Recommendationsmentioning

confidence: 99%

Utilizing Entities for an Enhanced Search Experience

Balog

2018

Entity-Oriented Search

View full text Add to dashboard Cite

Over the past decade, search engines have not only improved the quality of search results, but also evolved in how they interact with users. Modern search engines provide assistance to users throughout the entire search process, from formulating their information needs to presenting results and recommending additional content. This chapter presents a selection of topics, where entities are utilized with the overall aim of improving users' search experiences. First, in Sect. 9.1, we discuss techniques for assisting users with articulating their information needs. These include query assistance services, such as query autocompletion and query suggestions, and specialized query building interfaces. Next, in Sect. 9.2, we turn to the question of result presentation. In conventional document retrieval, the standard way of serving results is to display a snippet for each document, consisting of its title and a short summary. This summary is automatically extracted from the document with the aim of explaining why that particular document is relevant to the query at hand. Moving from documents to entities as the unit of retrieval, the question we need to ask is: How can one generate dynamic summaries of entities when displaying them as search results? Finally, in Sect. 9.3, we describe entity recommendation methods that present users with contextual suggestions, encourage exploration, and allow for serendipitous discoveries. We study the related entity retrieval problem in different flavors, depending on what kind of input is available to the recommendation engine. Furthermore, we address the question of explaining the relationship in natural language between entities presented to the user. We refer to Table 9.1 for the notation used in this chapter. 9.1 Query Assistance Chapter 7 dealt with query understanding from the machine's point of view. In this section, we bring the user's perspective to the forefront. How can a semantic search

show abstract

“…Tables 1 and 2 identify some studies that use data analysis techniques and which data types are used. [4], [15], [16] Natural Language Processing text [4] HTML Trees (DOM) text [5], [6] Link Prediction Collaboration Networks; Social Networks; Infrastructure Networks; Sports Networks; Biology Networks [7] Probabilistic Three-way Entity Model (TEM) text [8] Entity Linking Entities (text) [9], [10], [11] Naive Bayes Classifier Text and numeric values [12] Multilayer Perceptron, (MLP) Time series [13] Entity Recognition text [13], [14] Sentiment Analysis text [4], [15], [16] Natural Language Processing text [17], [18] Topic Modeling Probabilistic text [19] Latent Semantic Visualization Time-stamps [20] First Story Detection text [21] Event Extraction Entities (text) [22] Data Discovery text [13] Entity Recognition text [13], [14] Sentiment Analysis text [23] Image Recognition image…”

Section: Related Workmentioning

confidence: 99%

Exploring Data Analytics of Data Variety

Cruz

Sá

Pereira

2018

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

The Internet allows organizations managers access to large amounts of data, and this data are presented in different formats, i.e., data variety, namely structured, semi-structured and unstructured. Based on the Internet, this data variety is partly derived from social networks, but not only, machines are also capable of sharing information among themselves, or even machines with people. The objective of this paper is to understand how to retrieve information from data analysis with data variety. An experiment was carried out, based on a dataset with two distinct data types, images and comments on cars. Techniques of data analysis were used, namely Natural Language Processing to identify patterns, and Sentimental and Emotional Analysis. The image recognition technique was used to associate a car model with a category. Next, OLAP cubes and their visualization through dashboards were created. This paper concludes that it is possible to extract a set of relevant information, namely identifying which cars people like more/less, among other information.

show abstract

Learning to Recommend Related Entities to Search Users

Cited by 28 publications

References 17 publications

A topic recommender for journalists

A topic recommender for journalists

Utilizing Entities for an Enhanced Search Experience

Exploring Data Analytics of Data Variety

Contact Info

Product

Resources

About