at the 16th International Conference on Intelligent Software Methodologies, Tools, and Techniques (SOMET_17) will take place on September 26~28, 2017, in Kitakyushu city, Japan. 

Conference website:  http://somet2017.iwate-pu.net/

You may submit your contribution to the special session by stating the name RSSA2017, in the cover letter, or you just send the paper to the special session chair:

Dr. Roliana Ibrahim

As attachment By Email: roliana@utm.my

The growing of the Web as a medium for electronic and business transactions serves as
foundation for the development of recommender systems technology. On the one hand, the role of a recommender system is to ease the task of the Web to enable users to provide feedback about their likes or dislikes. However, we presently live in an information age, surrounded by several data in the form of blogs, papers, and reviews on different websites. This trend of data has led to increased information flow and open more avenues which have eventually caused more confusion to the users. As a result of this vast amount of data, the task of making individual decisions becomes more difficult. Consequently, it is important to make an informed decision, but extensive information can hinder the process of decision making. Thus, to save the users from this confusion and make the experience of accessing the web more pleasurable, a recommender system is a necessity.

On the other hand, sentiment analysis involves the use of Natural Language Processing (NLP), statistics, and machine learning methods to extract, identify, or otherwise characterize the sentiment content of a text unit. Sentiment analysis is referred to as opinion mining. Sentiment analysis has grown with the advent of web 2.0. The Internet is a platform where people express their views, emotions, and feelings towards products, individuals, and life in general. Nowadays, the internet is faced with a massive resource of conscience and large data. Therefore, sentiment analysis goal focuses on sentiment classification to automatically classify opinionated text as being negative, positive or neutral. To realize the goal of sentiment analysis, recommender system can serve as tools that can make valuable suggestions to the users or customers in this era of big data and globalization.

The objective of this special session is to draw researchers’ interest to the research area of recommender system and sentimental analysis or both. Specifically, we welcome contributions towards the development of models for modeling opinion based on recommender system, using NPL, statistics or machine learning methods.  As well as the development of approaches for opinion mining based on sentiment analysis using recommender system (such as information extraction, question answering, and summarization (accounting or multiple viewpoints).  In particular, attention are to be paid

1)      The applications of recommender system approaches on various domain or the use of case studies

2)      The applications of sentiment analysis approaches on different domain or the use of case studies

3)      The applications of sentiment analysis using recommender system as a solution to real life problem

4)      Experimental paper on both recommender and sentiment analysis

Research Papers describing advanced prototypes and design, systems, tools, techniques, schemes and general survey papers indicating the future direction of research are equally welcome.

Recommender system

  • Issues in recommender system: Scalability, accuracy, novelty, sparse, missing erroneous, malicious data, cold-start, confidence, robustness, risk, serendipity, adaptivity, etc.
  • Collaborative filtering using recommender system for subjectivity detection
  • Content management and modeling
  • Recommender systems applications
  • Recommender systems applications for social media
  • Measuring personalization effectiveness
  • Evaluation methods for recommender systems
  • Ownership of social media content
  • Multi-criteria decision recommender system
  • Product modeling, user opinion mining and data extraction
  • Knowledge-based recommender system
  • Hybrid recommender system
  • Security and privacy in social media
  • Trustworthiness and reliability on social media
  • Impact of context-awareness
  • Big data
  • Reproducibility based recommender system

Sentiment analysis

  • Subjectivity Detection
  • Sentiment of data prediction
  • Aspect-based sentiment summarization
  • Contrastive Viewpoint Summarization
  • Summarization of opinions using text data
  • Helpfulness of online comments/reviews prediction
  • Opinion-based entity ranking
  • Product feature extraction and selection
  • Opinion retrieval
  • Document level
  • Sentence level
  • Machine learning for sentiment classification
  • Lexical analysis
  • Sentiment polarity classification
  • Sentic computing concept level, cross-lingual and irony sarcasm

Special Session Organizers

Assoc. Prof. Roliana Ibrahim, Department of Information Systems, Faculty of Computing,Univesiti Teknologi Malaysia

Email: roliana@utm.my

Assoc. Prof. Dr Takeru Yokoi, Tokyo Metropolitan College of Industrial Technology, Tokyo, Japan

Email:  takeru@metro-cit.ac.jp

Assoc. Prof. Bay Vo, Ho Chi Minh City University of Technology, Vietnam. 

Email: vd.bay@hutech.edu.vn

Prof. Ali Selamat, Faculty of Computing, Univesiti Teknologi Malaysia

Email: aselamat@utm.my

Prof. Habibollah Haron, Faculty of Computing, Univesiti Teknologi Malaysia

Email: habib@utm.my

Asst. Prof. Lim Kok Cheng, Universiti Tenaga National, Malaysia

Email: KokCheng@uniten.edu.my