Joint Learning on Relevant User Attributes in Micro-blog

Authors: Jingjing Wang, Shoushan Li, Guodong Zhou

IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical studies demonstrate the effectiveness of our proposed approach to joint learning on relevant user attributes.
Researcher Affiliation Academia Natural Language Processing Lab, School of Computer Science and Technology Soochow University, Suzhou, 215006, China djingwang@gmail.com, {lishoushan, gdzhou}@suda.edu.cn
Pseudocode No No explicit pseudocode or algorithm blocks were found. The methodology is described using mathematical equations and textual explanations.
Open Source Code No No explicit statement about the release of their own source code (Aux-LSTM) was found. The provided links refer to third-party tools used in the research, not the authors' implementation.
Open Datasets No We collect our data set from Tencent Micro-blog, which is one of the most popular SNS websites in China. From this website, we crawl each user s homepage containing user information (e.g. name, profession, age, gender) and the posted messages. The paper describes the creation of their own dataset from a public source, but does not provide public access to their collected dataset.
Dataset Splits Yes For each kind of user attribute (i.e., profession, gender and age) classification task, we randomly split the users into a training set (80% users) and a test set (20% users). We also set aside 10% users from the training as the validation data which is used to tune learning algorithm parameters.
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, memory) used for running experiments were mentioned in the paper.
Software Dependencies No No specific software dependencies with version numbers (e.g., library names with versions) were mentioned, only general tools like 'Adagrad' and 'word2vec'.
Experiment Setup Yes The dimensionality of word vector is set to be 200. The window size is set as 5. In our Aux-LSTM model, λ is set to be 0.75 in order to reduce the influence of noisy information from auxiliary task. All the matrix and vector parameters are initialized with uniform distribution in [ p 6/(r + c), p 6/(r + c)] In order to avoid over-fitting, the dropout strategy is used in both the LSTM layer and auxiliary LSTM layer.