Vés al contingut principal

Configuració de les galetes

Fem servir galetes per assegurar les funcionalitats bàsiques del lloc web i per a millorar la teva experiència en línia. Pots configurar i acceptar l'ús de galetes, i modificar les teves opcions de consentiment en qualsevol moment.

Essencials

Preferències

Analítiques i estadístiques

Màrqueting

Aquesta proposta ha sigut acceptada

Intelligent recommendations

Avatar: DataForGoodBCN
DataForGoodBCN
Acceptada / En curs

When someone publishes a new proposal, a list of similar entries is displayed to avoid duplicates. The current recommendation algorithm calculates the similarity of each pair of proposals based on trigram (sets of 3-characters) comparison. This method, however, does not take into account the semantic aspects of the text and can be easily improved using simple Machine Learning techniques.

We suggest using a technique called word embeddings which consists of assigning to each proposal a multi-dimensional vector, in such a way that similar proposals (in terms of semantics) end up having close vectors. Therefore, the recommendations for a given proposal would be the proposals with the smallest distances between the vectors.

To calculate the vectors associated with each proposal, we suggest using pre-calculated vector embeddings for each word (of those more frequent in the Decidim vocabulary) and then calculating the average of all words appearing in the proposal. The pre-calculation of word vectors could be done offline by any person with medium knowledge of NLP (DataForGoodBCN, the community that has created this proposal, could provide these calculations).



Comentari

Confirmar

Si us plau, inicia la sessió

La contrasenya és massa curta.

Compartir