Author pages are created from data sourced from our academic publisher partnerships and public sources.
Share This Author
Adaptive web search based on user profile constructed without any effort from users
Experimental results show that search systems that adapt to each user's preferences can be achieved by constructing user profiles based on modified collaborative filtering with detailed analysis of user's browsing history in one day.
Scholarly paper recommendation via user's recent research interests
This model examines the effect of modeling a researcher's past works in recommending scholarly papers to the researcher and shows that filtering these sources of information is advantageous -- when the model prune noisy citations, referenced papers and publication history, it achieves statistically significant higher levels of recommendation accuracy.
Multi-Document Abstractive Summarization Using ILP Based Multi-Sentence Compression
The proposed approach identifies the most important document in the multi-document set and generates K-shortest paths from the sentences in each cluster using a word-graph structure, and selects sentences from the set of shortest paths generated from all the clusters employing a novel integer linear programming model.
Exploiting potential citation papers in scholarly paper recommendation
On a scholarly paper recommendation dataset, it is shown that recommendation accuracy significantly outperforms state-of-the-art recommendation baselines as measured by nDCG and MRR, when it is discovered using imputed similarities via collaborative filtering.
Addressing cold-start in app recommendation: latent user models constructed from twitter followers
This paper describes a method that accounts for nascent information culled from Twitter to provide relevant recommendation in such cold-start situations and significantly outperforms other state-of-the-art recommendation techniques by up to 33%.
Predicting the popularity of web 2.0 items based on user comments
By modeling comments as a time-aware bipartite graph, this work proposes a regularization-based ranking algorithm that accounts for temporal, social influence and current popularity factors to predict the future popularity of items.
A comprehensive evaluation of scholarly paper recommendation using potential citation papers
- Kazunari Sugiyama, Min-Yen Kan
- Computer ScienceInternational Journal on Digital Libraries
- 1 June 2015
On a publicly-available scholarly paper recommendation dataset, it is shown that recommendation accuracy significantly outperforms state-of-the-art recommendation baselines as measured by nDCG and MRR, when using the adaptive neighbor selection method.
FANG: Leveraging Social Context for Fake News Detection Using Graph Representation
This work proposes Factual News Graph, a novel graphical social context representation and learning framework for fake news detection that is scalable in training as it does not have to maintain all nodes, and it is efficient at inference time, without the need to re-process the entire graph.
Neural Multi-task Learning for Citation Function and Provenance
- Xuan Su, Animesh Prasad, Min-Yen Kan, Kazunari Sugiyama
- Computer Science, GeologyACM/IEEE Joint Conference on Digital Libraries…
- 18 November 2018
This work hypothesizes that these two tasks are synergistically related, and builds a model that validates this claim, and shows that they are indeed synergistic: by jointly training both tasks using multi-task learning, they demonstrate additional performance gains.
Refinement of TF-IDF schemes for web pages using their hyperlinked neighboring pages
Experimental results show that, generally, more accurate feature vectors of a target Web page can be generated in the case of utilizing the contents of its hyperlinked neighboring pages at levels up to second in the backward direction from the target page.