Applying natural language processing (NLP) based metadata extraction to automatically acquire user preferences

Paik, Woojin; Yilmazel, Sibel; Brown, Eric W.; Poulin, Maryjane; Dubon, Stephane; Amice, Christophe

doi:10.1145/500737.500757

Cited by 26 publications

(11 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…One central component of CBF is the user modeling process, in which the interests of users are inferred from the items that users interacted with. "Items" are usually textual, for instance emails [314] or webpages [315]. "Interaction" is typically established through actions, such as downloading, buying, authoring, or tagging an item.…”

Section: Content-based Filteringmentioning

confidence: 99%

Research-paper recommender systems: a literature survey

et al. 2015

View full text Add to dashboard Cite

In the last 16 years, more than 200 research articles were published about research-paper recommender systems. We reviewed these articles and present some descriptive statistics in this paper, as well as a discussion about the major advancements and shortcomings and an overview of the most common recommendation concepts and approaches. We found that more than half of the recommendation approaches applied content-based filtering (55 %). Collaborative filtering was applied by only 18 % of the reviewed approaches, and graph-based recommendations by 16 %. Other recommendation concepts included stereotyping, item-centric recommendations, and hybrid recommendations. The content-based filtering approaches mainly utilized papers that the users had authored, tagged, browsed, or downloaded. TF-IDF was the most frequently applied weighting scheme. In addition to simple terms, n-grams, topics, and citations were utilized to model users' information needs. Our review revealed some shortcomings of the current research. First, it remains unclear which recommendation concepts and approaches are the most promising. For instance, researchers reported different results on the performance of contentbased and collaborative filtering. Sometimes content-based filtering performed better than collaborative filtering and Linnaeus University, Kalmar, Sweden sometimes it performed worse. We identified three potential reasons for the ambiguity of the results. (A) Several evaluations had limitations. They were based on strongly pruned datasets, few participants in user studies, or did not use appropriate baselines. (B) Some authors provided little information about their algorithms, which makes it difficult to re-implement the approaches. Consequently, researchers use different implementations of the same recommendations approaches, which might lead to variations in the results. (C) We speculated that minor variations in datasets, algorithms, or user populations inevitably lead to strong variations in the performance of the approaches. Hence, finding the most promising approaches is a challenge. As a second limitation, we noted that many authors neglected to take into account factors other than accuracy, for example overall user satisfaction. In addition, most approaches (81 %) neglected the user-modeling process and did not infer information automatically but let users provide keywords, text snippets, or a single paper as input. Information on runtime was provided for 10 % of the approaches. Finally, few research papers had an impact on research-paper recommender systems in practice. We also identified a lack of authority and long-term research interest in the field: 73 % of the authors published no more than one paper on research-paper recommender systems, and there was little cooperation among different co-author groups. We concluded that several actions could improve the research landscape: developing a common evaluation framework, agreement on the information to include in research papers, a stronger focus on non-accuracy aspect...

show abstract

Section: Content-based Filteringmentioning

confidence: 99%

Research-paper recommender systems: a literature survey

et al. 2015

View full text Add to dashboard Cite

show abstract

“…This approach needs sophisticated programs to analyze documents and insert linguistic and semantic markups between words and phrases in documents for automatic metadata extraction. While the NLP approach achieved comparable performance to manually created metadata in both Liddy (2002) and Paik's (2001) experiments, it is uncertain if the same would be true in much larger collections and if the process would be economic.…”

Section: Related Researchmentioning

confidence: 99%

“…However, elements in metadata standards have inherited much of the structure and semantics used in traditional cataloging, which are more suited to a human cataloger entering data for the elements than to computer programs processing and generating metadata. Researchers have experimented with the natural language processing (NLP) approach to generating metadata automatically (Liddy et al, 2002; Paik et al, 2001). This approach needs sophisticated programs to analyze documents and insert linguistic and semantic markups between words and phrases in documents for automatic metadata extraction.…”

Section: Related Researchmentioning

confidence: 99%

Building interoperable vocabulary and structures for learning objects

Qin

Hernández

2005

J. Am. Soc. Inf. Sci.

View full text Add to dashboard Cite

The structural, functional, and production views on learning objects influence metadata structure and vocabulary. We drew on these views and conducted a literature review and in-depth analysis of 14 learning objects and over 500 components in these learning objects to model the knowledge framework for a learning object ontology. The learning object ontology reported in this paper consists of 8 top-level classes, 28 classes at the second level, and 34 at the third level. Except class Learning object, all other classes have the three properties of preferred term, related term, and synonym. To validate the ontology, we conducted a query log analysis that focused on discovering what terms users have used at both conceptual and word levels. The findings show that the main classes in the ontology are either conceptually or linguistically similar to the top terms in the query log data. We built an Exercise Editor as an informal experiment to test its ability to be adopted in authoring tools. The main contribution of this project is in the framework for the learning object domain and methodology used to develop and validate an ontology.

show abstract

“…In [70], author profiles in social media are mined to get hidden user profile information, while in [60] metadata is used to mine author profiles; the work [85] attempts automatic collection and summarization of personal profiles from various social networks and other sources, while [20] proposes linguistic features that help determine the natural language of a person writing in English (on a dataset of the First NLI Shared Task) and [66] determines a user's occupation by his or her tweets.…”

Section: User Profiling With Nlpmentioning

confidence: 99%

Word Embeddings for User Profiling in Online Social Networks

Alekseev¹,

Nikolenko²

2017

CyS

View full text Add to dashboard Cite

User profiling in social networks can be significantly augmented by using available full-text items such as posts or statuses and ratings (in the form of likes) that users give them. In this work, we apply modern natural language processing techniques based on word embeddings to several problems related to user profiling in social networks. First, we present an approach to create user profiles that measure a user's interest in various topics mined from the full texts of the items. As a result, we get a user profile that can be used, e.g., for cold start recommendations for items, targeted advertisement, and other purposes; our experiments show that the interests mining method performs on a level comparable with collaborative algorithms while at the same time being a cold start approach, i.e., it does not use the likes of an item being recommended. Second, we study the problem of predicting a user's demographic attributes such as age and gender based on his or her full-text items. We evaluate the efficiency of various age prediction algorithms based on word2vec word embeddings and conduct an extensive experimental evaluation, comparing these algorithms with each other and with classical baseline approaches.

show abstract

Applying natural language processing (NLP) based metadata extraction to automatically acquire user preferences

Cited by 26 publications

References 3 publications

Research-paper recommender systems: a literature survey

Research-paper recommender systems: a literature survey

Building interoperable vocabulary and structures for learning objects

Word Embeddings for User Profiling in Online Social Networks

Contact Info

Product

Resources

About