Please use this identifier to cite or link to this item: https://doi.org/10.1145/3184558.3191659
Title: Cold Start Thread Recommendation as Extreme Multi-label Classification
Authors: Kishaloy Halder 
Lahari Poddar 
Min-Yen Kan 
Keywords: Recommendation System
Cold Start
Extreme Multi-Label Classification
Neural Network
Discussion Forum
Issue Date: 2018
Publisher: Association for Computing Machinery
Citation: Kishaloy Halder, Lahari Poddar, Min-Yen Kan (2018). Cold Start Thread Recommendation as Extreme Multi-label Classification. XMLC for Social Media: WWW 2018 Companion: The 2018 Web Conference Companion : 1911-1918. ScholarBank@NUS Repository. https://doi.org/10.1145/3184558.3191659
Rights: Attribution 4.0 International
Abstract: In public online discussion forums, the large user base and frequent posts can create challenges for recommending threads to users. Importantly, traditional recommender systems, based on collaborative filtering, are not capable of handlingnever-seen-before items (threads). We can view this task as a form of Extreme Multi-label Classification (XMLC), where for a newly-posted thread, we predict the set of users (labels) who will want to respond to it. Selecting a subset of users from the set of all users in the community poses significant challenges due to scalability, and sparsity. We propose a neural network architecture to solve thisnew thread recommendation task. Our architecture uses stacked bi-directional Gated Recurrent Units (GRU) for text encoding along with cluster sensitive attention for exploiting correlations among the large label space. Experimental evaluation with four datasets from different domains show that our model outperforms both the state-of-the-art recommendation systems as well as other XMLC approaches for this task in terms of MRR, Recall, and NDCG.
Source Title: XMLC for Social Media: WWW 2018 Companion: The 2018 Web Conference Companion
URI: https://scholarbank.nus.edu.sg/handle/10635/172414
ISBN: 978-1-4503-5640-4
DOI: 10.1145/3184558.3191659
Rights: Attribution 4.0 International
Appears in Collections:Elements
Staff Publications

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
xmlc18.pdf1.35 MBAdobe PDF

OPEN

PublishedView/Download

Page view(s)

40
checked on Jan 15, 2021

Google ScholarTM

Check

Altmetric


This item is licensed under a Creative Commons License Creative Commons