An AI-Powered Emotion-Aware Conversational Support System for Personalized Emotional Well-Being

{"Individuals":[0],"frequently":[1],"experience":[2,201],"stress,":[3,93],"anxiety,":[4,94],"loneliness,":[5,92],"and":[6,23,44,58,99,119,123,170,193,205,234,238,255,265,294,315,318],"other":[7,328],"emotional":[8,140,313],"difficulties":[9],"that":[10,49,103,133,187,199,212,272,288],"often":[11],"remain":[12],"unaddressed":[13],"because":[14],"of":[15,102,146,164],"limited":[16],"access":[17],"to":[18,25,81,127,172],"counselling":[19],"resources,":[20],"social":[21],"stigma,":[22],"hesitation":[24],"seek":[26],"help":[27],"in":[28],"person.This":[29],"paper":[30],"extends":[31],"an":[32,151],"earlier":[33],"rulebased":[34],"sentiment":[35,83],"analysis":[36],"chatbot":[37],"into":[38],"a":[39,59,65,85,129,158,162,179,190,194,225,240,283,309,321],"comprehensive":[40],"AI-Powered":[41],"Emotional":[42],"Support":[43],"Mood":[45],"Tracking":[46],"Web":[47],"Application":[48],"combines":[50],"Natural":[51],"Language":[52],"Processing":[53],"(NLP),":[54],"Machine":[55],"Learning":[56],"(ML),":[57],"personalized":[60],"conversational":[61,79,108],"interface.Rather":[62],"than":[63,300],"classifying":[64],"user's":[66],"message":[67],"only":[68],"as":[69,90,178,224,308,320],"positive,":[70],"negative,":[71],"or":[72,96,175,183,219,277,296,326],"neutral,":[73],"the":[74,100,147,200,208,213],"proposed":[75,148],"system":[76,112,149,209,304],"analyzes":[77],"free-form":[78],"text":[80],"infer":[82],"polarity,":[84],"specific":[86],"emotion":[87],"category":[88],"(such":[89],"sadness,":[91],"anger,":[95],"low":[97],"motivation),":[98],"intensity":[101],"emotion,":[104],"while":[105],"also":[106],"retaining":[107],"context":[109],"across":[110],"turns.The":[111],"produces":[113],"empathetic,":[114],"nondiagnostic":[115],"responses,":[116],"generates":[117],"optional":[118],"nonintrusive":[120],"self-care":[121],"suggestions,":[122],"logs":[124],"each":[125],"interaction":[126],"build":[128],"longitudinal":[130],"mood-tracking":[131],"dashboard":[132],"helps":[134],"individuals":[135,290],"reflect":[136],"on":[137],"their":[138],"own":[139],"patterns":[141],"over":[142],"time.A":[143],"distinguishing":[144],"feature":[145],"is":[150,168,216,222,305],"optional,":[152],"user-configured":[153],"\\"Comfort":[154],"Profile,\\"":[155],"through":[156,282],"which":[157],"user":[159],"may":[160],"associate":[161],"photo":[163],"another":[165],"person":[166,215],"who":[167],"meaningful":[169],"comforting":[171],"them":[173],"(male":[174],"female,":[176],"such":[177],"family":[180],"member,":[181],"friend,":[182],"mentor)":[184],"along":[185],"with":[186,252],"person's":[188],"name,":[189],"favourite":[191],"quote,":[192],"preferred":[195],"support":[196,298,314],"style,":[197],"so":[198],"feels":[202],"more":[203],"personal":[204],"reassuring":[206],"without":[207],"ever":[210],"implying":[211],"depicted":[214],"actually":[217],"present":[218],"communicating.The":[220],"architecture":[221],"designed":[223],"full-stack":[226],"application":[227],"(React.jsfrontend,":[228],"Node.js/Express":[229],"backend,":[230],"Python-based":[231],"ML":[232],"microservice,":[233],"MongoDB":[235],"persistence":[236],"layer)":[237],"proposes":[239],"staged":[241],"model":[242],"comparison":[243],"between":[244],"rule-based":[245],"keyword":[246],"matching,":[247],"traditional":[248],"machine":[249],"learning":[250],"(TF-IDF":[251],"Logistic":[253],"Regression/SVM),":[254],"transformerbased":[256],"models":[257],"(BERT/DistilBERT),":[258],"evaluated":[259],"using":[260],"accuracy,":[261],"precision,":[262],"recall,":[263],"F1-score,":[264],"confusion-matrix":[266],"analysis.A":[267],"four-level":[268],"escalation":[269],"framework":[270],"ensures":[271],"messages":[273],"indicating":[274],"severe":[275],"distress":[276],"selfharm":[278],"risk":[279],"are":[280],"handled":[281],"clear,":[284],"non-motivational":[285],"safety":[286],"pathway":[287],"directs":[289],"toward":[291],"trusted":[292],"contacts":[293],"professional":[295],"emergency":[297],"rather":[299],"continued":[301],"casual":[302],"conversation.The":[303],"explicitly":[306],"positioned":[307],"supplementary,":[310],"non-clinical,":[311],"first-line":[312],"self-awareness":[316],"tool,":[317],"not":[319],"diagnostic":[322],"instrument":[323],"for":[324],"depression":[325],"any":[327],"mental":[329],"health":[330],"condition.":[331]}

Authors

Institutions

Publication Details

Journal
International Journal of Innovative Research in Technology
Published
2026-09-17
DOI
https://doi.org/10.64643/ijirt.208560-459
Primary Topic
Emotion and Mood Recognition
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
article

An AI-Powered Emotion-Aware Conversational Support System for Personalized Emotional Well-Being

Sunil Mahajan, Pranav Chitalkar, Omkar Jadhav, Tushar Badgujar
International Journal of Innovative Research in Technology
Emotion and Mood Recognition
article

An AI-Powered Emotion-Aware Conversational Support System for Personalized Emotional Well-Being

Sunil Mahajan, Pranav Chitalkar, Omkar Jadhav, Tushar Badgujar
article en

Abstract

Individuals frequently experience stress, anxiety, loneliness, and other emotional difficulties that often remain unaddressed because of limited access to counselling resources, social stigma, and hesitation to seek help in person.This paper extends an earlier rulebased sentiment analysis chatbot into a comprehensive AI-Powered Emotional Support and Mood Tracking Web Application that combines Natural Language Processing (NLP), Machine Learning (ML), and a personalized conversational interface.Rather than classifying a user's message only as positive, negative, or neutral, the proposed system analyzes free-form conversational text to infer sentiment polarity, a specific emotion category (such as sadness, loneliness, stress, anxiety, anger, or low motivation), and the intensity of that emotion, while also retaining conversational context across turns.The system produces empathetic, nondiagnostic responses, generates optional and nonintrusive self-care suggestions, and logs each interaction to build a longitudinal mood-tracking dashboard that helps individuals reflect on their own emotional patterns over time.A distinguishing feature of the proposed system is an optional, user-configured "Comfort Profile," through which a user may associate a photo of another person who is meaningful and comforting to them (male or female, such as a family member, friend, or mentor) along with that person's name, a favourite quote, and a preferred support style, so that the experience feels more personal and reassuring without the system ever implying that the depicted person is actually present or communicating.The architecture is designed as a full-stack application (React.jsfrontend, Node.js/Express backend, Python-based ML microservice, and MongoDB persistence layer) and proposes a staged model comparison between rule-based keyword matching, traditional machine learning (TF-IDF with Logistic Regression/SVM), and transformerbased models (BERT/DistilBERT), evaluated using accuracy, precision, recall, F1-score, and confusion-matrix analysis.A four-level escalation framework ensures that messages indicating severe distress or selfharm risk are handled through a clear, non-motivational safety pathway that directs individuals toward trusted contacts and professional or emergency support rather than continued casual conversation.The system is explicitly positioned as a supplementary, non-clinical, first-line emotional support and self-awareness tool, and not as a diagnostic instrument for depression or any other mental health condition.

International Journal of Innovative Research in TechnologyVol. 13(5)
National School of Leadership (IN), Myanmar Institute of Theology (MM), Department of Commerce (AU), G.S. Science, Arts And Commerce College (IN)
Reduced inequalities
Openalex Percentile: Top 7%
Emotion and Mood Recognition
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.