Using Word2Vec Recommendation for Improved Purchase Prediction

Esmeli, Ramazan; Bader-El-Den, Mohamed; Abdullahi, Hassana

doi:10.1109/ijcnn48605.2020.9206871

Cited by 18 publications

(10 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The word embedding learns linguistic regularities and semantics from the sentences and represents the words by vectorized representations [24]. Recently, some of the recommendation methods [24,26,4] used techniques from Word2Vec to represent text-based features, and some of the recommendation algorithms [25,13] applied the techniques to represent items.…”

Section: Recommendation With Word Embeddingmentioning

confidence: 99%

Tourism recommendation based on word embedding from card transaction data

2023

View full text Add to dashboard Cite

In the tourism industry, millions of card transactions generate a massive volume of big data. The card transactions eventually reflect customers? consumption behaviors and patterns. Additionally, recommender systems that incorporate users? personal preferences and consumption is an important subject of smart tourism. However, challenges exist such as handling the absence of rating data and considering spatial factor that significantly affects recommendation performance. This paper applies well-known Doc2Vec techniques to the tourism recommendation. We use them on non-textual features, card transaction dataset, to recommend tourism business services to target user groups who visit a specific location while addressing the challenges above. For the experiments, a card transaction dataset among eight years from Shinhan, which is one of the major card companies in the Republic of Korea, is used. The results demonstrate that the use of vector space representations trained by the Doc2Vec techniques considering spatial information is promising for tourism recommendations.

show abstract

Section: Recommendation With Word Embeddingmentioning

confidence: 99%

Tourism recommendation based on word embedding from card transaction data

2023

View full text Add to dashboard Cite

show abstract

“…There are various embedding models that learn item representations from words, sentences, or paragraphs. Among them, word embedding models such as Word2Vec [22], GloVe [25] and FastText [14] are widely used for many recommendation tasks [8], but they have limitations: the order of words is ignored, which leads to the loss of the syntactic and semantic meaning in sentences [41]. We therefore considered two state-of-the-art sentence embedding models instead, specifically Embeddings from Language Models (ELMo) and Sentence-BERT.…”

Section: Item Content Representationmentioning

confidence: 99%

Learning to Recommend Items to Wikidata Editors

Alghamdi¹,

Shi²,

Simperl³

2021

Preprint

View full text Add to dashboard Cite

Wikidata is an open knowledge graph built by a global community of volunteers. As it advances in scale, it faces substantial challenges around editor engagement. These challenges are in terms of both attracting new editors to keep up with the sheer amount of work, and retaining existing editors. Experience from other online communities and peer-production systems, including Wikipedia, suggests that personalised recommendations could help, especially newcomers, who are sometimes unsure about how to contribute best to an ongoing effort. For this reason, we propose a recommender system WikidataRec for Wikidata items. The system uses a hybrid of content-based and collaborative filtering techniques to rank items for editors relying on both item features and item-editor previous interaction. A neural network, named neural mixture of representations, is designed to learn fine weights for the combination of item-based representations and optimize them with editor-based representation by item-editor interaction. To facilitate further research in this space, we also create two benchmark datasets, a general-purpose one with 220, 000 editors responsible for 14 million interactions with 4 million items, and a second one focusing on the contributions of more than 8, 000 more active editors. We perform an offline evaluation of the system on both datasets with promising results. Our code and datasets are available at https://github.com/WikidataRec-developer/Wikidata_Recommender.

show abstract

“…It can perform effectively no matter how many words are included in the input vector, but is constrained by the corpus to the vector space. By incorporating the generalizable contexts into the model, Word2Vec has been proven to be more accurate than other models [9,34,35].…”

Section: Recommendation Modelsmentioning

confidence: 99%

Posting Recommendations in Healthcare Q&A Forums

2021

View full text Add to dashboard Cite

Online Q&A forums, unlike search engines, allow posting of various types of queries, thus attracting users to seek information and solve problems in specific domains. However, as insufficient knowledge leads to incomprehensible queries, unsuitable responses are common. We develop posting recommendation systems (RSs) to support users in composing reasonable posts and receiving effective answers. The posting RSs were evaluated by a user study containing 27 participants and three tasks to examine if users engaged more in the question generation process. Two medical experts were recruited to verify whether professionals can understand and answer posts supported by RSs. The results show that the proposed mechanism enables askers to produce posts with better understandability, which leads experts to devote more attention to answer their questions.

show abstract

Using Word2Vec Recommendation for Improved Purchase Prediction

Cited by 18 publications

References 40 publications

Tourism recommendation based on word embedding from card transaction data

Tourism recommendation based on word embedding from card transaction data

Learning to Recommend Items to Wikidata Editors

Posting Recommendations in Healthcare Q&A Forums

Contact Info

Product

Resources

About