An opinion mining approach for web user identification and clients' behaviour analysis

Dziczkowski, Grzegorz; Węgrzyn-Wolska, Katarzyna; Bougueroua, Lamine

doi:10.1109/cason.2013.6622605

Cited by 7 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Age group distribution was as follows: most respondents (47) fall into age group 15-30 years old, 25 respondents are between 30 and 45 years old, eleven were over 45 years old, the rest were under 15 years old. The education distribution of the respondents is as follows: primary school (9), middle school (30), high school (11) and university education (24). The last two questions in the general section of the survey were about TV watching habits.…”

Section: Methodsmentioning

confidence: 99%

“…Although research on opinion mining has been very active in the last decade, most of the work has focused on written text, predominantly in English; far less attention has been given to the problem of inferring users' opinions or interests from behavioral data. A survey of user opinion mining is presented in [11] and explores existing mechanisms for determining user opinion from text documents, specifically in the context of sentiment analysis and opinion mining using machine learning and classification techniques on documents.…”

Section: Related Workmentioning

confidence: 99%

“…The problem of analyzing user behavior to gain insight based on web-based data sources is addressed in [11]. The premise of our work is similar, but fundamental differences exist between web browsing and TV viewership information, which need to be taken into account.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Modeling Opinion of IPTV Viewers Based on Implicit Feedback and Content Metadata

2019

View full text Add to dashboard Cite

In today's hyper-connected world, rich social data feeds can be obtained from various sources, including the data exhaust of many commonly used systems. In this paper, we analyze the social pulse, obtained from viewer activity in an IPTV network-we attempt to validate a framework for determining public opinion and public interest through implicit feedback of IPTV viewers. First, we address the hypothesis that implicit viewer feedback in the form of channel change events, paired with the content metadata, can be used to model viewers' opinion and interest. For this, we design a controlled experiment to collect explicit feedback by rating a set of general-interest news clips. In addition to collecting demographic information, we also survey viewers' opinion, interest, and the probability of channel change during each clip. Furthermore, we extract weighted feature vectors from the closed captions of the video; this data, combined with the reported probability of channel change, is used to build a model that classifies opinion in five categories based on the probability of channel change and content. Next, we build a simplified model that classifies opinion in five categories based on the interest, which shows a linear relationship, but further consideration of content, in this case, provides better accuracy and possibility to analyze anomalous cases. Finally, we discuss and analyze the applications of such models in large systems and the necessary modifications to scale the system and to ensure the adequate performance on massive IPTV event data streams. INDEX TERMS Implicit user feedback, opinion modeling, interest modeling, viewership profiling, IPTV.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Modeling Opinion of IPTV Viewers Based on Implicit Feedback and Content Metadata

2019

View full text Add to dashboard Cite

show abstract

“…The data are gathered from the e-commerce sites that use the general approaches of web usage mining. Various classification methods are used for classifying the opinions based on the linguistic processing of natural language [10]. The object identification and polarity analysis are performed using the free-tagging methods for overcoming the challenges of processing the opinions of online comments.…”

Section: Related Workmentioning

confidence: 99%

Sentiment analyzer: Analysis of journal citations from citation databases

Parthasarathy

Tomar²

2014

2014 5th International Conference - Confluence the Next Generation Information Technology Summit (Confluence)

View full text Add to dashboard Cite

The process of finding out the frequency of citations for various journals or articles or research papers is known as citation analysis. The impact of any research paper can be found by computing the number of citations, the particular journal or paper received. Many researchers quote concepts or ideas from various papers and the final outcome of the paper in their discussion. But it does not always mean that all the authors and papers referred to would be criticizing the referred paper with positive words. Sometimes if the referring paper has produced good results when compared to the referred paper then obviously the authors do not give much positive comments in their discussion. In order to address this problem, we propose the sentiment analysis can be performed to rate the citations based on the polarity level. The sentence parser can be used to identify the adjectives what the authors used in their discussion about the cited paper. Then the identified adjectives can be assigned a score to distinguish it from positive and negative. In between, if any paper is found without clearly mentioning the cited paper with identifiable adjective terms then in can be named as unknown or neutral. The citations can be ranked based on the computed polarity score. The ranking process helps to project the citations which have cited with higher positivity content in their discussion.

show abstract

“…For example, Dziczkowski, Grzegorz and others survey research on the opinion mining approach for web user identification and clients' behaviour analysis [13], in this paper, an approach based on statistical analysis of natural language is proposed, three different methods are used for classifying opinions from clients' data, two new methods are introduced based on linguistic knowledge, in order to assign a mark dependent upon the client's emotions and opinions described in comments, the effect of experiments demonstrates that the system developed can carry out an evaluation and rating of opinions. Karakostas, Bill and others survey research on the MapReduce architecture for web site user behaviour monitoring in real time [14], in this paper, a MapReduce style architecture is proposed, where the processing of event series from the web users is performed by a number of cascading mappers, reducers, local to the event origin, the experimental results show that this architecture is capable to carry out time series analysis in real time for very large web data sets based on the actual events instead of resorting to sampling or other extrapolation techniques.…”

Section: Related Workmentioning

confidence: 99%

Model of Network Topic Detection Based on Web Usage Behaviour Mode Analysis and Mining Technology

Chen¹

2017

INT J COMPUT COMMUN

View full text Add to dashboard Cite

show abstract

An opinion mining approach for web user identification and clients' behaviour analysis

Cited by 7 publications

References 13 publications

Modeling Opinion of IPTV Viewers Based on Implicit Feedback and Content Metadata

Modeling Opinion of IPTV Viewers Based on Implicit Feedback and Content Metadata

Sentiment analyzer: Analysis of journal citations from citation databases

Model of Network Topic Detection Based on Web Usage Behaviour Mode Analysis and Mining Technology

Contact Info

Product

Resources

About