MovieMine: personalized movie content search by utilizing user comments

Kim, H. W.; Han, Keejun; Yi, Mun Yong; Cho, Joonmyun; Hong, Jin‐Woo

doi:10.1109/tce.2012.6415015

Cited by 23 publications

(15 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Kim et al [7], for example, proposed a personalized search engine for movies, called MovieMine, based on reviews and user-provided ratings. In this system, the user types a query, which is expanded by adding keywords taken from earlier reviews provided by himself, reflecting his preferences, allowing the search key to be customizable.…”

Section: Related Workmentioning

confidence: 99%

“…We select topics with the following value ranges: [2,7], [5,10], [5,100], [10,15], [10,50], [15,20], and [50, 100], where the first value corresponds to the minimum number of documents and the second value corresponds to the maximum number of documents. With these values, we explored different cluster granularities, which, in turn, allowed us to observe the specificity of the aspects; those produced in (sub)clusters with [2,7] documents are more specific, while those produced in (sub)clusters with [50, 100] documents are more generic. By experimentation, the granularity [2,7] provided the best results, as it contains more specific descriptions about the items.…”

Section: Extracting Aspects Through Hierarchy Clusteringmentioning

confidence: 99%

“…With these values, we explored different cluster granularities, which, in turn, allowed us to observe the specificity of the aspects; those produced in (sub)clusters with [2,7] documents are more specific, while those produced in (sub)clusters with [50, 100] documents are more generic. By experimentation, the granularity [2,7] provided the best results, as it contains more specific descriptions about the items. This configuration is used in the experimental evaluation presented in the "Empirical evaluation" section.…”

Section: Extracting Aspects Through Hierarchy Clusteringmentioning

confidence: 99%

“…Recent works focus on extending the traditional recommendation paradigms by using this user-provided unstructured information [6][7][8][9]. This is a great source of information, since it is able to describe the item and provide feedback about the opinion of the user regarding the item and its features.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Exploiting feature extraction techniques on users’ reviews for movies recommendation

D'Addio¹,

Domingues

Manzato³

2017

J Braz Comput Soc

View full text Add to dashboard Cite

Recommender systems help users to deal with the information overload problem by producing personalized content according to their interests. Beyond the traditional recommender strategies, there is a growing effort to incorporate users' reviews into the recommendation process, since they provide a rich set of information regarding both items' features and users' preferences. This article proposes a recommender system that uses users' reviews to produce items' representations that are based on the overall sentiment toward the items' features. We focus on exploiting the impact that different feature extraction techniques, allied with sentiment analysis, cause in an item attribute-aware neighborhood-based recommender algorithm. We compare four techniques of different granularities (terms and aspects) in two recommendation scenarios (rating prediction and item recommendation) and elect the most promising technique. We also compare our techniques with traditional structured metadata constructions, which are used as the baseline in our experimental evaluation. The results show that the techniques based on terms provide better results, since they produce a larger set of features, hence detailing better the items.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Extracting Aspects Through Hierarchy Clusteringmentioning

confidence: 99%

Section: Extracting Aspects Through Hierarchy Clusteringmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Exploiting feature extraction techniques on users’ reviews for movies recommendation

D'Addio¹,

Domingues

Manzato³

2017

J Braz Comput Soc

View full text Add to dashboard Cite

show abstract

“…Personalization in contemporary multimedia search engines is mostly accomplished in the same manner as in search engines that retrieve web-pages: by considering meta-information [22,32], such as the history of user queries [27] or spatio-temporal characteristics [28] in order to provide recommendations. However, the actual content of multimedia has not been widely used for personalization purposes, with few exceptions [26].…”

Section: Introductionmentioning

confidence: 99%

Accessibility-based reranking in multimedia search engines

Kalamaras

Dimitriou

Drosou

et al. 2016

Multimed Tools Appl

View full text Add to dashboard Cite

Traditional multimedia search engines retrieve results based mostly on the query submitted by the user, or using a log of previous searches to provide personalized results, while not considering the accessibility of the results for users with vision or other types of impairments. In this paper, a novel approach is presented which incorporates the accessibility of images for users with various vision impairments, such as color blindness, cataract and glaucoma, in order to rerank the results of an image search engine. The accessibility of individual images is measured through the use of vision simulation filters. Multi-objective optimization techniques utilizing the image accessibility scores are used to handle users with multiple vision impairments, while the impairment profile of a specific user is used to select one from the Pareto-optimal solutions. The proposed approach has been tested with two image datasets, using both simulated and real impaired users, and the results verify its applicability. Although the proposed method has been used for vision accessibility-based reranking, it can also be extended for other types of personalization context.

show abstract

Efficiency Evaluation of Recommender Systems: Study of Existing Problems and Possible Extensions

Sharma¹,

Ahuja²

2017

Information and Communication Technology for Sustainable Development

View full text Add to dashboard Cite

MovieMine: personalized movie content search by utilizing user comments

Cited by 23 publications

References 21 publications

Exploiting feature extraction techniques on users’ reviews for movies recommendation

Exploiting feature extraction techniques on users’ reviews for movies recommendation

Accessibility-based reranking in multimedia search engines

Efficiency Evaluation of Recommender Systems: Study of Existing Problems and Possible Extensions

Contact Info

Product

Resources

About