Improving Opinion Aspect Extraction Using Semantic Similarity and Aspect Associations

Authors: Qian Liu, Bing Liu, Yuanlin Zhang, Doo Soon Kim, Zhiqiang Gao

AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results using eight review datasets show the effectiveness of the proposed approach.
Researcher Affiliation Collaboration 1Key Lab of Computer Network and Information Integration (Southeast University), Ministry of Education, China 2School of Computer Science and Engineering, Southeast University, China 3Department of Computer Science, University of Illinois at Chicago, USA 4Department of Computer Science, Texas Tech University, USA 5Bosch research lab, USA
Pseudocode Yes Algorithm 1 AER(Dt, R , R+, O); Algorithm 2 Sim-recom(T , T ); Algorithm 3 AR-recom(T , T ).
Open Source Code No The paper mentions using an "open source tool word2vec" but does not state that its own methodology's source code is publicly available.
Open Datasets Yes We thus use two publicly available aspect-annotated corpora2. One is from (Hu and Liu 2004)... The other is from (Liu et al. 2015). 2http://www.cs.uic.edu/ liub/FBS/sentiment-analysis.html
Dataset Splits No The paper mentions using "Test Datasets for Evaluation" and discusses training word vectors and mining association rules from other datasets, but it does not specify explicit training, validation, and test splits for its proposed AER model in the typical sense.
Hardware Specification No The paper does not provide specific details about the hardware used for running experiments, such as CPU or GPU models.
Software Dependencies No The paper mentions using "word2vec" and "Stanford Parser" but does not specify their version numbers.
Experiment Setup Yes We empirically set the parameters for aspect similarities as ϵ = 0.38 in Algorithm 2, set the parameters for generating association rules as minimum confidence = 0.5 and minimum support = 0.2.