Human-computer interaction based on background knowledge and emotion certainty

View article
PeerJ Computer Science
This article was retracted on August 23, 2024. Read the retraction notice.

Main article text

 

Introduction

Proposed method

Problem definition

Emotional friendliness

where R(k) is the kth human-computer interaction emotion friendliness and takes values in the range [0, 1], where a smaller value indicates a worse emotional interaction state and, conversely, a larger value indicates a better emotional interaction state. In particular, an initial value of 0.5 indicates an uncertain human-computer interaction. W(k) is the interaction input affective evaluation value, with an initial value of 0 and a range of [−1, 1]. A positive value indicates a positive affective state, while a negative value indicates a negative affective state. The initial value of C(k) is 0, which indicates the reinforcing effect of consecutive positive or negative emotions. This means that when the affective tendencies are the same between the two conversations, the value of C(k) increases and the degree of certainty increases; when the affective tendencies are different between the two conversations, the degree of certainty decreases. In the following, W(k) and C(k) are defined.

Emotion assessment

where EP={pp,ap,𝕕p} denotes the interactive input emotion; l takes the values 1, 2, 3, 4, 5, and 6, representing the six emotions happy, surprised, disgusted, angry, fearful, and sad, respectively. El is the set of coordinates of the basic affective state in the PAD space, and Cl is the set of covariance matrices of the basic affective state in the PAD space; then hl is the distance between the interaction input affect Ep and the basic affect El obtained under the Cl constraint.

Emotion certainty

Knowledge graph ripple network interaction model

Knowledge graph ripple networks

where G is a known knowledge graph, hkis a dialogue entity, and k denotes the number of dialogue rounds. The triadic ripple set for the set Hk of obtained participant dialogue entities is defined as

where n indicates the entity at which level of association. For example, S11 denotes the level 1 associated entity of the dialogue entity in dialogue 1.

where RiKd×d, hiKd denote the entity vectors of the ripple set ri and hi respectively. The entity vectors of the ripple set triple (hi,ri,ti) are obtained from the knowledge graph feature learning method TransD (Liu, Xie & Wang, 2017), corresponding to the entity vectors denoted as hi, Ri and ti. The association probability pi can be viewed as the probability of measuring the similarity of a word vector v to an entity hi in the relational Ri-space.

where α,β is the constraint factor and has α+β=1 (the default will be α=β=0.5, as detailed later in the experimental discussion section). yv takes on a value range of [0, 1], with values closer to 1 indicating that the participant is more satisfied with the response.

Knowledge graph ripple network interaction model construction

Experimental studies

Settings

Evaluation metrics

where, k represents the number of conversations that participants participate in, rankqi represents the rank of the i-th participant’s reply in the reply set, Ave(Ai) represents the average accuracy of the reply sort of the i-th conversation model. p(j) represents the ranking level of the j-th answer in the adjusted reply set after the model adjusts the ordering of the candidate reply set considering the given limiting factors. r(j) represents the ranking of the j-th answer in the standard response set. n indicates the number of replies in the standard reply set. MAP reflects the average accuracy of the one-value accuracy of the recovery performance.

Experimental results

Experimental discussion

Conclusions

Supplemental Information

Training dataset.

DOI: 10.7717/peerj-cs.1418/supp-1

Source code (Python 3.6).

DOI: 10.7717/peerj-cs.1418/supp-3

Additional Information and Declarations

Competing Interests

The author declares that they have no competing interests.

Author Contributions

Qiang He conceived and designed the experiments, performed the experiments, analyzed the data, performed the computation work, prepared figures and/or tables, authored or reviewed drafts of the article, and approved the final draft.

Data Availability

The following information was supplied regarding data availability:

The raw data are available in the Supplemental Files.

The data is available at 2018 NLPCC task 7: http://tcci.ccf.org.cn/conference/2018/taskdata.php.

Funding

The author received no funding for this work.

1 Citation 1,383 Views 77 Downloads

Your institution may have Open Access funds available for qualifying authors. See if you qualify

Publish for free

Comment on Articles or Preprints and we'll waive your author fee
Learn more

Five new journals in Chemistry

Free to publish • Peer-reviewed • From PeerJ
Find out more