Mention Recommendation for Twitter with End-to-end Memory Network

By Haoran Huang, Qi Zhang, Xuanjing Huang. 2017

33 citations recorded by the source corpus.

In this study, we investigated the problem of recommending usernames when people attempt to use the ``@'' sign to mention other people in twitter-like social media. With the extremely rapid development of social networking services, this problem has received considerable attention in recent years. Previous methods have studied the problem from different aspects. Because most of Twitter-like microblogging services limit the length of posts, statistical learning methods may be affected by the problems of word sparseness and synonyms. Although recent progress in neural word embedding methods have advanced the state-of-the-art in many natural language processing tasks, the benefits of word embedding have not been taken into consideration for this problem. In this work, we proposed a novel end-to-end memory network architecture to perform this task. We incorporated the interests of users with external memory. A hierarchical attention mechanism was also applied to better consider the interests of users. The experimental results on a dataset we collected from Twitter demonstrated that the proposed method could outperform state-of-the-art approaches.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xing Xie
2. Hongwei Wang
3. Wenjie Li
4. Miao Zhao
5. Fuzheng Zhang
6. Minyi Guo
7. Gediminas Adomavicius
8. Xiangnan He

In Computer Vision and Pattern Recognition

1. Dietmar Jannach
2. Gediminas Adomavicius
3. Xing Xie
4. Robin D. Burke
5. Minyi Guo
6. Jialin Wang
7. Miao Zhao
8. Fuzheng Zhang

In Information Systems

1. Xing Xie
2. Dietmar Jannach
3. Miao Zhao
4. Wenjie Li
5. Hongwei Wang
6. Fuzheng Zhang
7. Xiangnan He
8. Minyi Guo

Citations in the corpus

• RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems (2018, background): “Researchers have also proposed using memory networks in other tasks such as sentiment classification [13, 27] and recommendation [5, 8].”
• Multistakeholder recommendation: Survey and research directions (2020, background): “opularity and in uence can also play a role [134, 67]. As a result, typical solutions combine graph-based, interaction-based, and content-based methods to produce the ultimate list of recommendations [134, 49, 64]. 5.3 Summary The examples of people recommendation we provided in this section show th”